Skip to main content
Glama
Guardian by Odingard

Guardian by Odingard

Get the records for a request

guardian_record
Read-onlyIdempotent

Look up the evidence records Guardian holds for a request to see what was decided and whether the call ran, without changing anything or running a tool.

Instructions

Look up the evidence records Guardian holds for one request, to see what was decided and whether the call ran. It changes nothing and runs no tool, so calling it again is safe. Returns the requestId and its list of records; an unknown requestId, or Guardian unreachable, returns ok: false with a reasonCode. Use it after an unknown or unclear outcome, before trying a call again.

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": {
      "requestId": "<requestId>"
    },
    "name": "guardian_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestIdYesThe requestId of an earlier call, from guardian_invoke_tool or guardian_claim. Starts with req_.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.3
    • addedInput schema / properties / requestId / description
      Added value: +"The requestId of an earlier call, from guardian_invoke_tool or guardian_claim. Starts with req_."
    • addedInput schema / properties / requestId / minLength
      Added value: +1
  2. First observedv0.5.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety claims are somewhat redundant. The description does add value beyond them by disclosing the return shape (requestId plus records) and the failure behavior: an unknown requestId or unreachable Guardian returns ok: false with a reasonCode. That error contract is genuinely useful information the annotations cannot convey.

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?

Three short sentences, each doing distinct work: purpose, safety/idempotency, return and failure contract, then the usage trigger. Front-loaded with the action and free of 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?

There is no output schema, and the description compensates by describing both the success payload and the ok: false failure mode with reasonCode. Combined with the annotations and fully documented single parameter, an agent has everything needed to call it and interpret results.

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 coverage is 100% and the schema itself explains that requestId comes from guardian_invoke_tool or guardian_claim and starts with req_. The description only refers to 'one request', adding no format or sourcing detail beyond the schema, so the 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?

The description uses a specific verb and resource: 'look up the evidence records Guardian holds for one request', with the added purpose of seeing 'what was decided and whether the call ran'. This clearly distinguishes it from guardian_invoke_tool and guardian_claim in substance, though neither sibling is named directly.

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?

It gives an explicit trigger: 'Use it after an unknown or unclear outcome, before trying a call again.' That is a clear when-to-use condition with a sequencing rule relative to retries, but it does not name the sibling tools or state exclusions by name.

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