Skip to main content
Glama

retry_job

Retry a failed media-processing job by moving it back to pending. Pass a unique idempotency key per intended retry to prevent duplicate attempts.

Instructions

Move a failed job back to pending. Pass a unique idempotency_key per intended retry.

    This tool does not ask for approval itself: the calling client does (Claude Desktop shows
    a confirmation; the bundled agent pauses at its approval node).
    

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": {
      "job_code": "<job_code>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "retry_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_codeYese.g. "MJ-0001"
idempotency_keyYes

Output Schema

NameRequiredDescriptionDefault
titleYes
statusYes
job_codeYes
source_idYes
created_atYes
updated_atYes
retry_roundYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Adds real context beyond the annotations: approval is client-side, not server-side, and each intended retry needs a fresh idempotency_key — consistent with idempotentHint=false and materially useful for an agent that might otherwise retry in a loop. Doesn't say what happens to prior run history or error records.

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?

The core action is front-loaded in the first sentence and nothing is redundant. The parenthetical about Claude Desktop and approval nodes is slightly verbose relative to its value but still earns its place as behavioral context.

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?

An output schema exists, so return values need no explanation, and both required parameters are accounted for. For a two-parameter mutation tool, the description covers action, precondition, idempotency contract, and approval flow — enough to call it correctly.

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?

Coverage is 50% (job_code documented in the schema; idempotency_key is not). The description partly compensates by explaining the key must be unique per intended retry, but gives no format or generation guidance, so it is only a marginal lift over the schema.

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 concrete verb and resource plus an explicit state transition: 'Move a failed job back to pending.' That distinguishes it from submit_job (new work) and get_job_status (read), though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'failed job' — the precondition is clear enough. But it never says what to do instead for non-failed jobs (submit_job) or how to inspect failures first (list_job_errors), so the routing decision is left to inference.

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