Poll a job

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

Annotations only provide readOnlyHint=true, and the description adds meaningful behavior: progress fields are populated only for certain stages, and it returns log tail, failure-artifact paths, and a feedbackHint on genuine failure. No contradiction with annotations.

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?

The description is a single dense sentence that front-loads the core fields and packs in useful specifics like the stages for which progress is populated and failure artifact details. It is somewhat heavy due to parentheticals, but every element earns its place.

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 that an output schema exists, the description sufficiently covers what is returned, including status, stage, progress, log tail, result/error, failure artifacts, and feedbackHint. It omits explicit lifecycle or polling guidance, such as when a job is considered complete, but this is not a critical gap.

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 schema documents tailLines with a default, while jobId has no description, but 'of a pipeline job' implies its role as the job identifier. The description clarifies return contents rather than parameter-specific semantics, only partially compensating for the 50% schema coverage.

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 clearly states that the tool returns status, stage, per-scene progress, log tail, and final result/error for a pipeline job. This is specific enough to distinguish it from siblings like job_list and job_cancel.

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 title 'Poll a job' implies its intended use for checking job progression, but there is no explicit when-to-use or when-not-to-use guidance against alternatives such as job_list or job_cancel. Usage context is mostly inferred rather than stated.

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