Openpowerlifting

Opl Records

opl_records

Read-onlyIdempotent

All-time best powerlifting performances from the OpenPowerlifting database: the top lifters by total, squat, bench, deadlift or Dots points for a sex and equipment category, optionally narrowed by weight_class (e.g. "83", "84+"), federation, age_class (e.g. "24-34"), tested (drug-tested meets only) and year. One row per lifter (their best qualifying entry), with the meet and date. Lifts are in kilograms. total is only ranked over full three-lift (SBD) entries unless event is given. These are the best entries IN THE DATA, filtered as asked -- not an official federation record list (federations apply their own rules and equipment definitions). Nothing matching returns found:false with data_as_of.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "sex": "M",
      "limit": 5,
      "equipment": "Raw",
      "weight_class": "93"
    },
    "name": "opl_records"
  }
}

Input Schema

Name	Required	Description
`sex`	Yes	M, F or Mx.
`lift`	No	What to rank by (default total).
`year`	No	Only meets in this year.
`event`	No	SBD, B, D, BD, SB... Default SBD for lift=total; none otherwise.
`limit`	No	Lifters to return, 1-50 (default 10).
`tested`	No	true = drug-tested meets only.
`age_class`	No	e.g. "24-34", "40-44".
`equipment`	No	Default Raw.
`federation`	No	Federation code, e.g. "IPF".
`weight_class`	No	e.g. "83", "93", "120+".

Output Schema

Name	Required	Description	Default
`sex`	No
`rows`	No
`event`	No
`found`	No
`source`	No
`licence`	No
`returned`	No
`equipment`	No
`ranked_by`	No
`data_as_of`	No
`latest_meet_date`	No
`copy_refreshed_at`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses real behavioral traits: results are one row per lifter (their best qualifying entry) with meet and date, weights are in kilograms, total is ranked only over full SBD entries unless event is supplied, and an empty match returns found:false with data_as_of. That is exactly the kind of edge-case disclosure annotations cannot carry.

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 dense sentences with the purpose and filter list front-loaded and the important caveat (not official records) near the end. It is appropriately sized for a 10-parameter tool, though the filter enumeration partly duplicates the schema and could be trimmed.

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

Completeness5/5

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

An output schema exists so return-value explanation isn't required, yet the description still flags units, grain, default behavior and the found:false path. Combined with the official-records caveat, an agent has everything needed to call this correctly and interpret the result.

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 the schema already documents each parameter, and the baseline would be 3. The description earns extra credit for cross-parameter semantics the schema does not state — that the total ranking silently restricts to three-lift entries unless event is given, and that a default equipment of Raw applies.

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 — all-time best powerlifting performances from OpenPowerlifting — and names the ranking dimensions (total, squat, bench, deadlift, Dots). The 'one row per lifter' framing and the explicit non-equivalence with official federation record lists distinguish it clearly from the sibling lookup tools opl_lifter_history and opl_meet_results.

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?

Usage context is strong: it explains that this is a leaderboard of best entries in the data, filtered by the listed facets, and explicitly warns that results are not an official federation record list. What's missing is explicit routing — it never names opl_lifter_history or opl_meet_results as the alternatives for individual career or meet-level lookups.

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

All Openpowerlifting tools Inspect

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.