Job result

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

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds valuable context beyond annotations: error behavior for incomplete jobs, structured failure reason for failed jobs, and the result field carrying the output path and probe for successful ones. This fully discloses behavioral traits.

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?

Two sentences, front-loaded with the primary purpose, and each sentence adds essential information (purpose and error/result behavior). No filler or redundancy.

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?

Given the single parameter, existing output schema, and strong annotations, the description fully covers all necessary context: what to do first, what error paths exist, and what the successful result contains. It is complete for a tool of this complexity.

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?

The input schema has 100% coverage with the parameter 'job_id' described as 'Job id returned when the work was queued'. The tool description does not add further parameter-specific detail, but since the schema already covers it, the baseline of 3 applies. No additional semantics are needed.

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?

The description states a specific verb ('Fetch') and resource ('output paths of a completed job'), clearly distinguishing it from siblings like job_status (status) and cancel_job (cancellation). It leaves no ambiguity about the tool's core function.

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?

The description explicitly warns that the tool errors if the job hasn't finished and instructs to 'poll job_status first', naming the alternative tool and providing clear sequencing. It also notes the different behavior for failed vs. successful jobs, giving actionable usage context.

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