Skip to main content
Glama

Compare / rank

compare

Evaluate multiple subjects against one rubric to produce a ranked leaderboard, helping you identify which candidate performs best.

Instructions

Evaluate several subjects against one rubric and return a ranking (leaderboard).

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": {
      "rubric": "<rubric>",
      "subjects": "<subjects>"
    },
    "name": "compare"
  }
}

Input Schema

NameRequiredDescriptionDefault
rubricYes
subjectsYes
idempotencyKeyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.9/5.0
Behavior2/5

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

No annotations exist, so the description carries the full burden, and it only discloses the output concept ('ranking (leaderboard)'). It says nothing about whether running a comparison creates a persisted evaluation record, whether it is expensive or long-running, how file/url/image/youtube subjects are fetched, or what an 'idempotencyKey' implies about retry behavior — a meaningful gap for a tool whose schema implies remote fetching and likely state creation.

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?

A single sentence, front-loaded with the action and ending with the concrete output shape. There is no filler, though brevity here borders on under-specification rather than tightness.

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

Completeness2/5

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

Given a deeply nested input schema with six polymorphic input types, no output schema, and no annotations, one sentence is not enough. The agent lacks guidance on subject construction, rubric forms, cost/side effects, and the exact leaderboard payload, all of which the structured fields do not supply.

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

Parameters2/5

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

Schema description coverage is 0%, and the description only alludes to two of the three parameters ('rubric', 'subjects') by name-like wording, adding no detail about rubric being either a string or an object map, subject 'name'/'inputs' structure, the minimum of two subjects, or the six supported input modalities. The 'idempotencyKey' parameter is entirely unmentioned in both schema and description.

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 description gives a specific verb pair (evaluate/rank), the resource being ranked (several subjects against one rubric), and the output (a leaderboard). An agent can tell this is the multi-subject, ranking-producing variant of an evaluation, though it never explicitly contrasts itself with the sibling named 'evaluate'.

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: 'several subjects' plus 'return a ranking' suggests this is for comparative batch scoring rather than a single evaluation. There is no explicit when-to-use/when-not statement and no sibling is named as an alternative, so an agent must infer the boundary with 'evaluate' or 'create_rubric' on its own.

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