Read a job

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context: the result is a status, and only once the job is done does it include the full answer, which tells the agent to expect partial/empty content while pending. It omits error behavior for unknown ids and any polling cadence guidance.

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?

A single sentence with the action front-loaded and the conditional return value trailing. No filler and nothing redundant.

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 carries the burden of describing return values, and it does so at a summary level (status plus full answer when done). For a one-parameter read tool this is nearly sufficient; status enumerations and failure modes are left unstated, which is the only 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?

Schema coverage is 100% and the single id parameter is documented with its provenance (send_job or list_jobs). The description adds no further meaning about the id format or validity. Baseline 3 applies since the schema does all the work.

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?

"Read one job" gives a specific verb and resource, and "one" implicitly contrasts with the sibling list_jobs. It also names the payload (status, and the full answer when done), so an agent can tell what it retrieves. It does not explicitly name list_jobs as the alternative, so it stops 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?

The phrase "when it is done" implies this is polled to check completion, and the schema notes the id comes from send_job or list_jobs, which situates it in a workflow. But the description itself never states when to use it versus list_jobs or why to prefer one over the other. Usage is inferable rather than stated.

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