Skip to main content
Glama
Sign In

agentcheck

by io.github.agentwares
OverviewDiscussionsAdmin

agentcheck_record

Record one production interaction with your agent (the prompt or messages, the final answer, the tools it called, optionally the model) as a trace on a target. Call it from your agent or from a proxy in front of it after each task; promote a good trace with agentcheck_promote_trace to replay it nightly and catch regressions. Requires an API key.

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": {
      "targetId": "<targetId>",
      "input": "<input>",
      "output": "<output>"
    },
    "name": "agentcheck_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoshort label, e.g. 'refund for order A-1029'
inputYesthe prompt, the messages array, or an object with prompt/messages
modelNothe model that produced this answer, so drift re-runs can compare across models
outputYesthe agent's final answer
targetIdYesid from agentcheck_create_target or GET /api/v1/targets
toolCallsNotool calls in order

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / model / description
      Added value: +"the model that produced this answer, so drift re-runs can compare across models"
    • addedInput schema / properties / targetId / description
      Added value: +"id from agentcheck_create_target or GET /api/v1/targets"
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the write/non-idempotent nature is already conveyed structurally. The description adds genuinely useful context beyond that: it is a write operation that creates a trace on a target, and it 'Requires an API key' — an auth prerequisite the annotations do not express. It stops short of describing return payload or failure behavior.

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?

Front-loaded with the core action and its payload, then usage, then the sibling hand-off. Two sentences carry a lot without padding, though the parenthetical field list is slightly dense.

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

Completeness4/5

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

For a six-parameter mutation tool with no output schema and full schema description coverage, the description covers purpose, invocation timing, sibling routing, and the API-key prerequisite. The only soft gap is what the call returns (a trace id), which no output schema promises, so this is close to complete.

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 100%, so all six parameters are documented in the schema itself (e.g. targetId points at agentcheck_create_target, model exists for drift comparison across models). The description mirrors those fields but adds no syntax, format, or ordering detail beyond the schema's baseline.

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

Purpose5/5

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

States a specific verb ('Record') and resource ('one production interaction ... as a trace on a target'), and enumerates the captured payload (prompt/messages, final answer, tool calls, model). It is clearly distinguishable from siblings, and even names agentcheck_promote_trace as the follow-on step.

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

Usage Guidelines5/5

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

Explicitly says where and when to call it ('from your agent or from a proxy in front of it after each task') and routes the agent onward with 'promote a good trace with agentcheck_promote_trace to replay it nightly and catch regressions.' The use condition and the alternative are both spelled out.

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

All agentcheck toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources