Check a job's running, done, or failed state, progress, and final result by job ID to track work started by another call.
State (running / done / failed), progress and, once done, the result of a job started by another call.
| Name | Required | Description | Default |
|---|---|---|---|
| job | Yes | Job id from the call that started it. |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive), so the description's contribution is the state machine and the fact that the result only materializes once done — genuinely useful beyond structured data. It doesn't say whether results/state expire or are retryable after failure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, front-loaded with the state enumeration, and every clause (states, progress, result-once-done) carries information. No filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description does its job by naming the return fields (state, progress, result). Missing only guidance on polling cadence vs jobs_wait and whether the result is retrievable repeatedly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the sole parameter already documents 'Job id from the call that started it.' The description's line about jobs started by another call merely echoes the schema, adding no format or sourcing detail beyond it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (get) and resource (job) and enumerates the observable states (running/done/failed) plus progress and result. It does not differentiate from the sibling jobs_wait, which likely covers the blocking-wait variant, 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'a job started by another call' implies usage as a poller for ids returned by async tools, which is useful implied context. But it never says when to use this instead of jobs_wait, nor whether repeated polling is expected versus a single blocking call.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.