Skip to main content
Glama

Where a rating sits

rating_percentile
Read-onlyIdempotent

Where one Lichess or chess.com rating sits among the club players, team members and people on both sites whose settled ratings Club Ladder reads: the share below it and the percentiles of that pool. Give lichess or chesscom (exactly one) and time_control. Use for questions like whether a rating is good.

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": {
      "time_control": "<time_control>"
    },
    "name": "rating_percentile"
  }
}

Input Schema

NameRequiredDescriptionDefault
lichessNoA Lichess rating.
chesscomNoA chess.com rating.
time_controlYesTime control. Each site and time control is its own rating pool.

Output Schema

NameRequiredDescriptionDefault
p10No
p25No
p75No
p90No
noteNo
siteYes
medianNo
ratingYes
sourceYes
percentileYes
time_controlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: the pool is restricted to 'settled ratings' (implying provisional ratings are excluded) and spans club players, team members, and both sites. It does not describe behavior on a rating outside the pool range or on an empty pool, which keeps it from a 5.

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?

Two sentences, with the scoping of the pool and the returned statistics front-loaded before the operational instruction. The opening sentence is dense and slightly tangled ('whose settled ratings Club Ladder reads'), but no sentence is filler and the alternative phrasing would cost more than it saves.

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-shape explanation is correctly omitted, and the description covers the pool definition and the one-of-site constraint that the schema fails to express. What remains unstated is edge behavior - a rating with no comparable pool members, or values near the schema bounds - which matters for a statistical lookup but is a minor gap overall.

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?

Schema coverage is 100%, so parameter naming and ranges are already documented and baseline would be 3. The description nevertheless adds a real constraint absent from the schema: lichess and chesscom are mutually exclusive and 'exactly one' is required, while the JSON schema only requires time_control. That closes a genuine ambiguity in the structured data.

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 names a concrete operation on a concrete resource: placing one Lichess or chess.com rating within a defined player pool and returning the share below it plus percentiles. It also characterizes the reference population ('club players, team members and people on both sites whose settled ratings Club Ladder reads'), which is far more than a restatement of the name. It stops short of 5 because it never distinguishes itself from the sibling estimate_rating, which an agent could plausibly confuse with a percentile lookup.

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?

It offers one usage cue ('Use for questions like whether a rating is good') and the invocation constraint of supplying exactly one site rating plus time_control. There is no when-not-to-use statement and no routing to estimate_rating or any other sibling, so an agent must infer the boundary itself. Usage is implied rather than delimited.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.