{"uid":"cap_EN5eqQtX84Hpq5R11GmLc","slug":"toolfit-by-youraitools-full-ai-agent-tool-schema-audit-04d77c56","name":"ToolFit by YourAITools – Full AI Agent Tool Schema Audit","description":"Full AI agent tool schema audit API (MCP and function calling). Full audit of an agent tool list (tools array or public remote MCP URL): every schema issue per provider (OpenAI, Anthropic, Gemini, Bedrock, MCP; strict mode opt-in) with JSON path and source link, rewritten definitions per provider, confusable tool pairs with distinguishing terms and fix hints, description and poisoning lints, per-tool fingerprints and a pin.","url":"https://api.youraitools.co/toolfit/v1/full?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":[],"properties":{"url":{"type":"string","description":"Public remote MCP server URL (Streamable HTTP, https), e.g. https://api.youraitools.co/mcp/hub. ToolFit only lists its tools."},"tools":{"type":"array","items":{"type":"object"},"description":"Tool definitions: MCP tools/list entries, OpenAI {type:\"function\",function:{...}}, Anthropic {name,description,input_schema}, Gemini functionDeclarations or Bedrock toolSpec. Max 500."},"providers":{"type":"array","items":{"enum":["openai","openai_strict","anthropic","gemini","bedrock","mcp"],"type":"string"},"description":"Providers to check (default openai, anthropic, gemini, bedrock, mcp; add openai_strict for Structured Outputs strict mode). GET: comma list."}},"description":"Search intents: tool schema audit, mcp tool rewrite, function calling fix, gemini schema compatibility, tool poisoning check, agent tools quality"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"pin":{"type":"object"},"fixed":{"type":"object"},"grade":{"type":"string"},"score":{"type":"number"},"tools":{"type":"number"},"issues":{"type":"array"},"tokens":{"type":"object"},"poisoning":{"type":"object"},"providers":{"type":"object"},"confusable":{"type":"object"}}}}}}},"responseSchema":{"type":"json","example":{"pin":{"set_id":"ts_0123456789abcdef0123456789abcdef"},"fixed":{"openai":{"changed":8}},"grade":"D","score":62,"tools":31,"issues":[{"path":"description","rule":"description_length","tool":"read_url","provider":"openai","severity":"error"}],"tokens":{"avg":374,"total":11585},"poisoning":{"high":0,"findings":0},"providers":{"gemini":{"errors":9,"compatible":false},"openai":{"errors":8,"compatible":false},"anthropic":{"errors":0,"compatible":true}},"confusable":{"high":1,"count":5}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_c18WMuRqi7cr02y-Z2Qmu","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Performs a comprehensive schema audit of an agent's tool list or remote MCP server, returning per-provider issues, rewritten definitions, confusable tool pairs, poisoning lints, and fingerprints.","exampleAgentPrompt":"Can you run a full schema audit on my tool list against OpenAI, Anthropic, and Gemini — I need to see every error with the JSON path, get rewritten definitions that pass each provider, and flag any tools that look confusable or have poisoning risks?","exampleUseCases":[{"title":"Pre-deployment tool compatibility check","prompt":"Before I deploy my agent, audit these 15 tool definitions against OpenAI strict mode and Anthropic — show me every schema error by JSON path and give me fixed versions I can drop straight in."},{"title":"MCP server tool quality audit","prompt":"Audit the tools on my public MCP server at https://api.example.com/mcp for all five providers — I want a compatibility grade, a list of issues, and a flag if any tool descriptions look like they could be poisoned."},{"title":"Diagnosing confusable tools in a large fleet","prompt":"I have 50 tools in my agent and it keeps calling the wrong one — can you audit them and specifically highlight which tool pairs are confusable, with hints on how to make their descriptions more distinguishable?"}],"resultDescription":"Returns a JSON object with: an overall compatibility grade (e.g. 'D') and numeric score, total tool count, an array of issues each with tool name, provider, rule, severity, and JSON path, per-provider compatibility flags and error counts, rewritten (fixed) tool definitions per provider with change counts, confusable tool pairs with high-risk count and distinguishing hints, poisoning findings with severity counts, token usage stats (avg and total), and a fingerprint pin (set_id) for the audited tool set.","failureModes":["Invalid or unreachable MCP URL returns an error indicating the server could not be fetched","Tool array exceeding 500 entries is rejected","Missing required 'type' or 'method' fields in input causes a 400 validation error","Unsupported provider enum value returns a validation error","Payment failure (x402) blocks the request before processing","Malformed tool JSON in the tools array may cause partial or failed analysis"],"whenToPreferThis":"Choose this endpoint when you need a single comprehensive audit covering all major LLM providers (OpenAI including strict mode, Anthropic, Gemini, Bedrock, MCP) at once, rather than provider-specific validators. It is especially valuable when you need rewritten definitions ready to use, poisoning/injection detection, confusable tool diagnosis, and a stable fingerprint pin for tracking tool set changes over time — capabilities not available in generic JSON Schema validators.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-25T12:31:10.869Z","isFirstParty":false,"canonicalSlug":"toolfit-by-youraitools-full-ai-agent-tool-schema-audit-04d77c56"}