Skip to main content
Glama

research_metrics

Read-onlyIdempotent

Read study denominators, preflight and production counts, and accounted costs for a task, keeping unknown accounting explicit so totals stay traceable to the host's original trace.

Instructions

Read study denominators, preflight/production counts and accounted costs. Unknown accounting remains explicit. Tool/model/human-intervention totals require the host's original trace.

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": {
      "task_id": "<task_id>"
    },
    "name": "research_metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, closed-world behavior, so the description clears the lower bar. It adds real context the annotations cannot carry: unknown accounting is surfaced explicitly rather than imputed, and certain totals are deliberately out of scope without the host's trace, warning the agent that results may be partial.

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?

Three short sentences, front-loaded with the returned data and ending on the trace caveat, with no filler. The telegraphic phrasing ("study denominators") is dense but each clause carries information.

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?

An output schema exists, so return shapes need not be spelled out, and with one parameter and no nesting the tool is simple. The description covers scope and the key caveats about unknown accounting and missing totals, leaving only the task_id semantics unaddressed.

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

Parameters4/5

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

Only one parameter exists (task_id) with 0% schema description coverage, so the description must compensate and it does so adequately: it frames the tool as operating on a single study/task's metrics, which makes the sole identifier's role inferable. It never states the accepted format or whether the task must already exist, so a small gap remains.

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?

"Read study denominators, preflight/production counts and accounted costs" gives a specific verb plus a concrete inventory of what is returned, which is well beyond a tautology. It never names a sibling or says explicitly how it differs from logging or event tools, so it stops short of full differentiation.

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

Usage Guidelines3/5

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

Usage is only implied: the note that "tool/model/human-intervention totals require the host's original trace" functions as a partial when-not, telling the agent this tool will not supply those aggregates. There is no positive statement of when to reach for this instead of a related introspection tool.

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