Job Status

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

The annotations already declare readOnlyHint=true, but the description adds significant behavioral context: the exact return shape, status enum, elapsed_s, meta, an error field on failure, and the explicit guarantee that the result payload is omitted. This tells the agent exactly what will and will not happen when invoking the tool.

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 compact sentence with no wasted words. It front-loads the tool's purpose and immediately covers the key behavioral facts: cheap, loop-friendly, no payload.

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?

For a simple one-parameter polling tool, the description is complete. It explains what the tool does, when to use it, what the return fields are, and what is intentionally absent. No output schema exists, but the description covers the return contract sufficiently.

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 0%, but there is only one parameter, job_id, whose purpose is self-evident. The description adds meaning by specifying that the job_id comes from any *_submit tool, which is enough context for an agent to supply it correctly.

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 ('poll') and resource ('async job from an *_submit tool'), and clearly distinguishes itself from result-fetching tools by noting it returns status without the result payload. It is unmistakably different from job_result and job_list even without opening their schemas.

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 gives clear context: use this for lightweight polling of async jobs and it is cheap to call in a loop. It implies the alternative is fetching the result payload elsewhere, but it does not explicitly name job_result or state when not to use this tool.

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