Agentic Keychain

Get benchmark evidence

get_benchmark

Read-onlyIdempotent

Registry-run benchmark summaries (labelled), publisher claims (labelled PUBLISHER CLAIMED) and the signed attestations of one capability. Use when: you want the measurements behind an answer (paired runs, model, fixtures, method) or want to check them yourself. Not for: an answer for your task (evaluate_capability) or artifact hashes and the log proof (get_provenance). Input: a capability id, ak:// URI or slug. Output: ak.benchmark.v1 with the evidence, the publisher claims, the attestations, the method and the limitations; publisher claims never decide anything.

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": {
      "capability": "<capability>"
    },
    "name": "get_benchmark"
  }
}

Input Schema

Name	Required	Description	Default
`capability`	Yes	Capability id (ak:publisher:name or ak:publisher:name:x.y.z), ak:// URI or slug.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 28, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds behavioral context beyond annotations: it labels publisher claims as 'PUBLISHER CLAIMED' and states 'publisher claims never decide anything', which is a decision-relevance caveat an agent would not infer from annotations. It does not describe empty-result or error behavior, but the added provenance-qualification is substantive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded purpose, then Use when / Not for / Input / Output in compressed labelled segments, with no filler sentences. Each clause carries routing or format information.

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?

This is a read-only, openWorld=false, idempotent lookup with one required parameter and no output schema. The description supplies what is missing: the output type (ak.benchmark.v1), the elements of the evidence (paired runs, model, fixtures, method, limitations, attestations), and the publisher-claim caveat. Nothing an agent needs to call it correctly is absent.

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 baseline is 3, but the description adds accepted input formats ('a capability id, ak:// URI or slug') and, via the output line, signals the expected ak.benchmark.v1 shape. The schema already documents the id/URI/slug formats, so the incremental value over structured data is modest rather than large.

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?

Uses a specific verb+resource ('Registry-run benchmark summaries', 'publisher claims', 'signed attestations of one capability') and explicitly names the sibling tools it is not (evaluate_capability, get_provenance), so an agent can distinguish it without opening any 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?

The tool states an explicit 'Use when' condition ('you want the measurements behind an answer ... or want to check them yourself') and a 'Not for' exclusion, naming the two alternatives (evaluate_capability for task answers, get_provenance for artifact hashes and log proof). This is exactly the routing guidance an agent needs among 11 siblings.

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

All Agentic Keychain 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.

Resources

Need Help?