ToolChoice

Your MCP server works.
But will an agent choose the right tool?

Run realistic tool-selection tests, uncover ambiguous tools, and improve your MCP server before agents fail in production.

No signup. Your tools are never executed.

example report

A six-tool CRM server, deliberately ambiguous: get_customer, search_customers and search_contacts absorb each other's traffic. See the confusion matrix and the simulated fix.

View example report
the gap schema validation leaves

Why valid schemas still fail

get_customer vs search_customers

Both descriptions say they retrieve customer information. Neither says whether the identifier must already be known. A linter passes both; an agent flips a coin.

required: ["id"] — but which id?

The schema is valid. The model still passes an email into id because nothing documents the cus_ prefix.

cancel_invoice — no warning

Destructive tools that don't state their consequences get called casually. That's not a schema error. It's a behavioral one.

workflow

Paste, measure, fix

  1. 1

    Paste tools/list JSON

    No signup, no connection required. The audit runs on your definitions alone — your tools are never executed.

  2. 2

    Test selection behavior

    Tool-selection tests run with structured output at temperature 0 — against a live model when configured, or the deterministic synthetic simulator (always labeled) when not. Demo audits score against human-authored fixtures.

  3. 3

    Rerun before you trust a rewrite

    Rewrites follow a strict shape — action, context, when to use, when not to — and the identical suite is rerun against them. Improvements are only claimed when the second evaluation supports them, in the same labeled mode.

confusion matrix
expectedselected insteadcount
get_customersearch_customers4
search_contactslist_contacts2
create_invoiceupdate_invoice2

Every misroute is explained: likely cause, then a concrete fix.

before → after (synthetic example)

“Gets customer data.”

“Retrieve one customer by their unique customer ID. Use this tool when the customer ID is already known. Do not use it to search by name, email, or company.”

68/100 84/100 · identical test suite, rerun — regressions are shown too

supported inputs
MCP tools/list JSONJSON-RPC responsesbare tool arraysOpenAPI 3.x JSON.json uploadbuilt-in demo servers

Remote MCP endpoint connection ships next — with SSRF protection, response limits, and no tool invocation.

methodology

Deterministic rules and LLM judgments never mix. Static findings are reproducible byte-for-byte; behavioral tests are ground-truth validated and run at temperature 0; the final score is a fixed weighted formula that no model can invent. Read the full methodology →

pricing

Free

$0
  • · 10 behavioral tests per audit
  • · Up to 20 tools · one model
  • · Temporary reports (7 days)
  • · Basic export

Developer

$19/mo
  • · 100 tests per month
  • · Saved audit history
  • · Private reports · full export
  • · Before/after comparisons
  • · Multiple model presets
Request early access

Team

$79/mo
  • · Team workspace
  • · CI + GitHub integration
  • · Scheduled audits · regression alerts
  • · API access
Request early access

Know whether agents choose the right tool.

Test your MCP tools against realistic user requests. Find ambiguous tools, missing descriptions, parameter confusion, and selection failures before your users do.

Run a free audit