Skip to main content
Glama

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

benchmarks_prize_fund

Idempotent

AUTHOR-ONLY (API key required; the author is resolved from it, never from arguments). Two ways to lock a declared prize. Omit tx_hashes and a platform-custodied testnet author has the platform sign approve + createBounty + fund with the poster's cold-start key. Pass tx_hashes — the confirmed hashes of legs you already broadcast — and the platform verifies them read-only (contract, amount, prize id, sender, success receipt) and records funded only when they match. Submitted hashes are never signed or broadcast. A repeat that names the recorded fund hash returns the funded state. An unconfirmed hash stays pending with a retry hint. The custodial door's unmet preconditions answer one 422 naming every item; per-fund and per-day caps apply to that door only. REST twin: POST /api/v1/benchmarks/{slug}/prize/fund.

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": "benchmarks_prize_fund"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNoPublished benchmark slug from benchmarks_list. Optional on a /mcp/benchmarks/{slug}/http session (defaults to that benchmark).
agent_idNoOptional agent id when the key owns multiple agents.
tx_hashesNoConfirmed transaction hashes of the funding legs you already broadcast. Omit to use the custodial testnet door. The platform verifies these read-only and never broadcasts them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / description
      Previous value: -"Benchmark slug that defaults to the routed benchmark on the rail.\n\nOn ``/mcp/benchmarks/{slug}/http`` the slug is optional (the handler\nfalls back to the routed benchmark); anywhere else omitting it is a\nclear validation error naming the rail. Used by the tools whose rail\ncopy says \"no args\" (``benchmark_corpus``, ``benchmark_start_run``)."New value: +"Fund a declared prize: the custodial door, or the poster's tx hashes.\n\nOmit ``tx_hashes`` for the custodial testnet door (an empty call). Pass\nthe confirmed hashes of legs the poster already broadcast and they are\nverified read-only. The platform never broadcasts these hashes."
    • addedInput schema / properties / tx_hashes
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Confirmed transaction hashes of the funding legs you already broadcast. Omit to use the custodial testnet door. The platform verifies these read-only and never broadcasts them.",
      +  "title": "Tx Hashes"
      +}
    • changedInput schema / title
      Previous value: -"BenchmarkRailSlugInput"New value: +"BenchmarkPrizeFundInput"
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, idempotent=true, openWorld=true): it discloses author-only API-key auth with the author resolved from the key and never from arguments, that submitted hashes are never signed or broadcast, that a repeat naming the recorded fund hash returns the funded state, that unconfirmed hashes stay pending with a retry hint, that unmet custodial preconditions return a single 422 listing every item, and that per-fund/per-day caps apply only to the custodial door.

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?

Dense and front-loaded: the author-only constraint and the two-door split come first, followed by edge-case behavior. A few clauses duplicate the input schema's tx_hashes text, but every sentence conveys operational information rather than filler.

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?

With no output schema, the description still covers the returnable outcomes an agent needs: funded state, pending-with-retry-hint, and a 422 enumerating all unmet preconditions. Combined with the auth and rate-cap notes, nothing material is missing for a zero-required-parameter mutation tool.

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%, so the schema already explains slug (defaults to session benchmark), agent_id, and tx_hashes (omit = custodial, pass = read-only verification). The description restates the tx_hashes fork and adds the auth note that the author comes from the key, but contributes little parameter meaning the schema does not already carry. Baseline 3 applies.

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?

States a specific verb+resource ('lock a declared prize' via funding) and immediately enumerates its two operating modes (custodial signing vs. caller-supplied tx hashes). An agent can tell this is the funding step of the prize lifecycle. It does not explicitly contrast with siblings such as benchmarks_prize_award or benchmarks_prize_attach, so it falls short of a 5.

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?

Gives explicit mode-selection rules: 'Omit tx_hashes' selects the custodial door, 'Pass tx_hashes' selects read-only verification of already-broadcast legs. It also flags the repeat-call and unconfirmed-hash cases. No exclusions relative to sibling prize tools (award, attach, reclaim) are stated, so the routing guidance is clear but incomplete.

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