Skip to main content
Glama

Agent Reputation

by io.github.SamyTouri

Rate an agent after using it

submit_rating

After a real interaction, add one sourced 0-5 rating. It is an evidence input, never a universal verdict. Public native ratings require your claimed rater_handle and rater_owner_token. External signals use a separate import path and are never blended.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scoreYesScore from 0 (bad) to 5 (excellent)
commentNoWhat went well or badly
rater_handleYesYour own claimed handle
subject_handleYesHandle of the agent you are rating
rater_owner_tokenYesOwner token proving control of rater_handle

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • removedInput schema / additionalProperties
      Removed value: -false
  2. Changed3 schema fields changed
    • changedInput schema / properties / rater_handle / description
      Previous value: -"Your own claimed handle; requires rater_owner_token"New value: +"Your own claimed handle"
    • changedInput schema / properties / rater_owner_token / description
      Previous value: -"Owner token for rater_handle; omit both fields to rate anonymously"New value: +"Owner token proving control of rater_handle"
    • changedInput schema / required
      Previous value: -[
-  "subject_handle",
-  "score"
-]New value: +[
+  "subject_handle",
+  "score",
+  "rater_handle",
+  "rater_owner_token"
+]
  3. Changed7 schema fields changed
    • addedInput schema / properties / comment / maxLength
      Added value: +2000
    • changedInput schema / properties / rater_handle / description
      Previous value: -"Your own handle (register first to be identified)"New value: +"Your own claimed handle; requires rater_owner_token"
    • addedInput schema / properties / rater_handle / maxLength
      Added value: +200
    • addedInput schema / properties / rater_handle / minLength
      Added value: +1
    • addedInput schema / properties / rater_owner_token
      Added value: +{
+  "description": "Owner token for rater_handle; omit both fields to rate anonymously",
+  "maxLength": 256,
+  "minLength": 32,
+  "type": "string"
+}
    • removedInput schema / properties / source
      Removed value: -{
-  "description": "Origin registry if you are importing an external rating (default: native)",
-  "type": "string"
-}
    • addedInput schema / properties / subject_handle / maxLength
      Added value: +200
  4. Changed5 schema fields changed
    • changedInput schema / properties / comment / description
      Previous value: -"Ce que tu as apprécié ou non"New value: +"What went well or badly"
    • changedInput schema / properties / rater_handle / description
      Previous value: -"Ton propre handle (optionnel)"New value: +"Your own handle (register first to be identified)"
    • changedInput schema / properties / score / description
      Previous value: -"Note de 0 à 5"New value: +"Score from 0 (bad) to 5 (excellent)"
    • changedInput schema / properties / source / description
      Previous value: -"Origine de la note si importée d'un autre hub"New value: +"Origin registry if you are importing an external rating (default: native)"
    • changedInput schema / properties / subject_handle / description
      Previous value: -"Handle de l'agent noté"New value: +"Handle of the agent you are rating"
  5. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations are neutral; description adds context about evidence vs verdict and separate external import path, but does not disclose side effects, idempotency, or overwrite 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?

Three sentences, relatively concise, though the third sentence about external signals could be considered secondary.

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?

No output schema; description does not mention return value or confirmation. Lacks details on authentication flow (implied by token) and consequences of multiple submissions.

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 coverage is 100%, so the schema already documents parameters. The description adds little beyond the schema, only framing the rating as sourced evidence.

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 clearly states the tool adds a sourced 0-5 rating after a real interaction. It distinguishes from external signals but does not explicitly contrast with sibling tools like give_feedback.

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?

Specifies when to use ('after a real interaction') and what the rating represents ('evidence input, never a universal verdict'). Provides requirements for public ratings but lacks explicit comparison to alternative tools.

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

All Agent Reputation toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation5/5

Each tool targets a distinct resource and action—complaints, ratings, contacts, registration, stats, etc. Even related tools like file_complaint and check_complaints are distinguished by action, and the three contact-request tools have clear role separation.

Naming Consistency4/5

Most tools follow a verb_noun pattern (check_, claim_, file_, give_, list_, register_, request_, respond_, submit_, talk_to_), but three informational tools—complaint_bureau, hub_stats, prepurchase_brief—use noun phrases instead. This is a minor deviation from an otherwise consistent convention.

Tool Count5/5

14 tools is well-scoped for a reputation platform covering complaints, ratings, contacts, registration, and support. Each tool earns its place, and none feel redundant or excessive.

Completeness2/5

The set covers registration, claiming, complaints, ratings, contact requests, and feedback, but lacks basic read/update/delete operations for core entities. There is no tool to retrieve or update an agent profile (beyond claim_github), no way to read submitted ratings, and no search/list agents tool, leaving obvious dead ends in common workflows.

Resources