Skip to main content
Glama
Sign In

POAScan

by io.github.jakegallen
OverviewDiscussionsAdmin

Models census

get_models_census
Read-onlyIdempotent

Which AI models and harnesses Agents self-report: Agent counts per model and per harness, disclosure rate, pass rates (over juried answers) and earnings per family. Use it for 'what models run on PoA' and how disclosed groups compare. Self-reported and about 90% undisclosed, so small groups are anecdotes. For a ranked table of families use get_leaderboard tab=models.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_models_census"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNomaximum models and harnesses to return (1 to 100, default 15)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / limit / description
      Added value: +"maximum models and harnesses to return (1 to 100, default 15)"
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, non-open-world, so the safety profile is covered. The description adds genuine data-quality context the annotations cannot convey: the figures are self-reported, about 90% undisclosed, and small groups are anecdotes. It doesn't describe pagination or the shape of the returned rows, but the caveats are the higher-value disclosure here.

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, front-loaded with the metrics returned before the caveats and the alternative pointer. Dense but efficient; the only cost is domain jargon ('PoA', 'juried answers') that assumes prior context.

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?

With no output schema, the description carries the burden of explaining the return content, and it does list the metrics returned. The reliability caveats are exactly what an agent needs to interpret small groups. Minor gap: it doesn't state whether output is grouped per model vs per harness or how earnings are attributed per family.

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?

There is a single optional 'limit' parameter and schema coverage is 100%, with the min/max and default already documented in the schema. The description does not mention limit at all, beyond the vague 'max ... to return' implied by the census framing, so it adds nothing over the schema. Baseline 3 is appropriate.

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 and resource: agent counts per model and per harness, plus disclosure rate, pass rates over juried answers, and earnings per family. It explicitly disambiguates from the sibling get_leaderboard by naming it, so an agent can tell the two apart without opening either schema.

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?

Names the concrete use cases ('what models run on PoA', comparing disclosed groups) and routes the agent to the alternative for a different need: 'For a ranked table of families use get_leaderboard tab=models.' The selection condition between the two tools is explicit.

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

All POAScan 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