Skip to main content
Glama

E-Commerce — Refund Request Audit — Kestrel Outfitters (2b20046e)

benchmark_award_evidence

Idempotent

✅ No API key needed. Fetch a benchmark's award-evidence pack after a verifiable award. Use it to recompute the root, digests, ranks and winners yourself. Arg: slug (defaults to the routed benchmark). Returns benchmark, test_set (with gold and salts, revealed only after the award), winners, rank_derivation, pack_hash, pack_anchor. Before the award it answers not_found naming the missing fact. Keyless and keyed calls get the same pack. REST twin: GET /api/v1/benchmarks/{slug}/award-evidence. Next: benchmark_commitment to compare the root.

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": "benchmark_award_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNoBenchmark slug from benchmarks_list or benchmarks_search. Optional on a /mcp/benchmarks/{slug}/http session (defaults to that benchmark).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, it discloses that no API key is needed, that keyless and keyed calls return the same pack (reinforcing idempotency), that gold and salts are only revealed after the award, and what the pre-award failure looks like. The readOnlyHint=false vs 'Fetch' pairing is explained in part by the one-time reveal of salts, so it reads as staged disclosure rather than a contradiction.

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?

Information is front-loaded (auth note, purpose, argument, return fields, edge case, REST twin, next step) and nearly every clause carries signal, though the leading checkmark emoji is decorative noise and the return-field list could be tightened.

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?

For a single-optional-parameter tool with no output schema, the description enumerates the returned payload (benchmark, test_set with gold and salts, winners, rank_derivation, pack_hash, pack_anchor) and covers the pre-award failure path, leaving nothing essential unspecified.

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 description coverage is 100% and the schema already documents that slug defaults to the routed benchmark on a rail session; the description's 'Arg: slug (defaults to the routed benchmark)' adds no new syntax or format meaning beyond that. Baseline 3 applies when the schema carries the parameter semantics.

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?

The description opens with a specific verb and resource ('Fetch a benchmark's award-evidence pack') plus a gating condition ('after a verifiable award'), which separates it from result-listing siblings such as benchmark_get_results and from benchmark_commitment, which it explicitly routes to as the comparison step.

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?

It states the purpose of using it ('recompute the root, digests, ranks and winners yourself'), names the next tool in the workflow ('benchmark_commitment to compare the root'), and gives an explicit when-not case ('Before the award it answers not_found naming the missing fact').

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.

Resources