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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: it is a polling endpoint, cost is per-file, and the payload includes verification detail plus a 'next step', which tells the agent this tool drives the workflow rather than just reporting a flag.

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 dense sentence followed by one imperative polling instruction, front-loaded with the scope ('Per file'). No wasted clauses, though the field list is packed tightly enough that readability suffers slightly.

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 returns and does so at a useful level of abstraction (state, verification, blockers, open questions, next step). What is missing is what a completed or terminal state looks like and how to distinguish it, which would complete the polling loop.

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% with both parameters documented, including that job_token comes from upload_statements and language defaults to 'de'. The description adds no parameter-level detail beyond the schema, so baseline 3 applies.

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 names the resource (job status) and enumerates what is returned per file: processing state, verification results, format readiness with blockers, open questions and next step. It is clearly a status/verification read, distinguishable from siblings like download_result or get_preview. Minor deduction for domain jargon ('KP's verification') that an agent without context may not parse.

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?

Explicitly instructs polling 'every few seconds until every file is read', which is real operational guidance. It stops short of naming alternatives or when-not-to-use (e.g., use list_open_questions to resolve blockers, download_result once ready), so the routing is implied rather than stated.

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