job_wait

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

With no annotations, the description carries the full burden and does well: it discloses that a timeout does not cancel slicing, that the returned state is durable, that queued/running implies more polling, and that restarted jobs stay interrupted and are never auto-repeated. It omits only auth/permission and any rate-limit or concurrency notes.

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?

Three short sentences, front-loaded with the 30-second cap and zero filler. Slight loss for the awkward line-broken phrasing, but every sentence carries information.

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?

An output schema exists, so return-value explanation is not required, and the description covers the state-revisit contract. What is missing for a polling tool with zero annotation coverage is the parameter contract and how this differs from job_status.

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 description coverage is 0%, so the description must compensate. It clarifies that the wait is capped at 30 seconds and that timing out is harmless, but never explains job_id, nor that timeout_seconds defaults to 10, nor the valid range below the 30s cap.

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?

Specific verb + resource: waits on a 'saved job' with a bounded 30-second horizon. It is distinguishable from job_cancel and jobs_list by the waiting semantics, but it never names job_status/job_log as the non-blocking siblings, so an agent must infer which polling tool to pick.

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?

'queued/running means call again' gives an explicit polling loop, which is real usage guidance. However there is no statement of when to prefer this over job_status or jobs_list, nor when-not to use it (e.g. for a job that was never started).

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