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

Annotations already declare readOnly/non-destructive/openWorld, so the safety profile is covered; the description adds valuable context beyond that — the full status vocabulary and the fact that the call does not process the document and is normally not billed. It stops short of explaining polling behaviour or what 'hitl' entails.

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, front-loaded clauses with zero filler: what it returns, what it does not do, and the endpoint. Every sentence 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?

With no output schema, the enumerated status list effectively documents the return value, and the billing note covers a key operational concern. Only minor gaps remain (polling guidance, meaning of 'hitl'), which are not essential to invoke the tool correctly.

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 100% and there is a single required job_id, so the schema carries the burden. The description only restates that a job identifier identifies the job; it adds no format, source, or validation detail beyond the schema.

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?

Names a specific verb and resource ('The status of one async capture job') and enumerates the exact states returned (in_queue, processing, hitl, done, error, closed, rejected). This clearly separates it from the value-returning siblings get_async_job_result and get_async_job_logs, and the endpoint confirms the scope.

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?

It signals scope with 'one async capture job' and clarifies 'Does not process a document; normally not billed', which hints at when it is safe/cheap to call. But it never explicitly routes the agent to alternatives such as get_async_job_result once a job is done, or list_async_jobs for polling many jobs, so usage is only implied.

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