Skip to main content
Glama

record_test_evidence

Idempotent

Needs sign-in (connect this server with OAuth, or pass an API key as the Authorization: Bearer header). Record actual browser test outcomes for this build. Include browser, viewport, player identities, inputs, expected/observed behavior, and artifact paths. A passed result is explicitly agent-reported. Unrun cases stay not_run. Never submit inferred results from source inspection.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "sessionId": "<sessionId>",
      "evidence": "<evidence>"
    },
    "name": "record_test_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
evidenceYes
sessionIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare a non-read-only, idempotent, non-destructive, closed-world write; the description adds auth requirements (OAuth or bearer header) and the crucial provenance rule that passed results are agent-reported, which annotations cannot express. It stops short of saying what happens on re-submission for an existing session, which matters given idempotentHint=true. No contradiction with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, each doing distinct work: auth, action, content, status semantics. The auth preamble precedes the purpose statement, which slightly delays the front-loading, but it is genuinely necessary information rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no output schema, the description covers auth, content expectations, and status rules well. It leaves unresolved whether evidence is appended or replaces prior entries for a session (the idempotent hint suggests the latter) and what the tool returns, which an agent needs to know before resubmitting.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the load: it usefully specifies what belongs in the nested detail string (browser, viewport, player identities, inputs, expected/observed behavior, artifact paths). It says nothing about sessionId — where it comes from or how it relates to start_test_session — and never references the 22-value case enum or the 4000-character detail limit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The second sentence gives a specific verb and resource: "Record actual browser test outcomes for this build," which is unmistakably a write of test evidence. It does not, however, distinguish itself from siblings such as test_report or close_test_session, so an agent cannot tell from the text alone which of those to reach for.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit negative guidance is given — "Never submit inferred results from source inspection" and "Unrun cases stay not_run" — which directly answers the main misuse risk for this tool. What is missing is a positive routing statement (e.g., use test_report to read results back, use start_test_session to obtain a sessionId), so alternatives are implied rather than named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources