Skip to main content
Glama
Guardian by Odingard

Guardian by Odingard

Run an approved request

guardian_claim
Destructive

Claim an approved ASK request to execute the held tool call once with its original arguments and return the execution record; unapproved, expired, or unknown requests are denied.

Instructions

Run a request that guardian_invoke_tool held as ASK, once the person has approved it in Guardian. Guardian issues the capability and runs the approved call with its original arguments (it can change the target system), then returns ALLOW with the execution record. Before approval it returns ASK again and runs nothing; a denied, expired or unknown requestId returns DENY with a reasonCode; Guardian unreachable fails closed (SERVICE_UNAVAILABLE) and can be retried. An approval is used once: claiming the same requestId again does not run the call a second time.

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_claim"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestIdYesThe requestId that guardian_invoke_tool returned with decision ASK. 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 that guardian_invoke_tool returned with decision ASK. Starts with req_."
    • addedInput schema / properties / requestId / minLength
      Added value: +1
  2. First observedv0.5.1

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing that the original arguments are reused, that the target system can be changed, that the capability is issued on approval, that approvals are single-use ('claiming the same requestId again does not run the call a second time'), and the exact outcome codes (ALLOW/DENY/SERVICE_UNAVAILABLE) including fail-closed and retryability. The single-use claim is consistent with idempotentHint=false and destructiveHint=true rather than contradicting them.

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?

Front-loaded with the primary action and precondition, then the success path, then failure modes, then the one-shot rule. Every clause carries a distinct behavioral fact; the density is high but nothing is redundant.

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-parameter, no-output-schema tool sitting in a multi-step approval flow, the description supplies everything an agent needs: precondition, execution semantics, all outcome classes, retry guidance, and the non-repeatable nature of an approval.

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% and already documents requestId as the ASK-state identifier prefixed with req_. The description adds the meaning that matters for safe use: the requestId must originate from guardian_invoke_tool's ASK decision and is consumed on first successful claim.

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 ('Run a request') and ties it precisely to the ASK state produced by the sibling guardian_invoke_tool, so an agent can distinguish it from initiating a call. The scope ('once the person has approved it in Guardian') is unambiguous.

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?

Explicitly names the precondition (prior guardian_invoke_tool returned ASK and a human approved), the negative case (before approval it returns ASK and runs nothing), and the failure cases (denied/expired/unknown, unreachable). The alternative flow is implied clearly enough that an agent knows to call guardian_invoke_tool first.

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