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

Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds real value beyond that by enumerating the response state machine and explaining that 'failed' carries a reason and 'refused' means the file needs a choice only the page can offer — a non-obvious behavioral detail. It omits polling/rate behavior and expiry timing, hence 4 rather than 5.

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 tightly-packed sentence with no filler, and the most discriminating information (which job, which states) comes first. The parenthetical about 'refused' is slightly buried at the end, which keeps it from a perfect score.

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 one-parameter read tool with no output schema, enumerating the possible states effectively substitutes for documenting return values, which is exactly what an agent needs. Missing only lifecycle/operational detail such as how long jobs live or whether repeated polling is expected.

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?

Only one parameter, documented at 100% coverage as 'The id convert_file answered with', so the schema already carries the semantics. The description reinforces the link to convert_file but adds no format or sourcing detail beyond the schema; baseline 3 is appropriate.

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 precisely ('the state of a conversion started by convert_file') and ties it to the sibling that creates the job, so an agent can tell it apart from convert_file and result_link. It is a noun phrase rather than an explicit verb ('check/poll'), which keeps it just 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?

Usage is only implied: the phrase 'started by convert_file' suggests polling after a conversion request, and the 'expired'/'refused' states hint at terminal conditions. There is no explicit statement of when to call it versus result_link or conversion_notes, and no guidance on polling cadence or when to stop.

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