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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new behavioral context: results are partial during conversion ('pages done of the total') and the download link only exists 'once it is ready', which tells the agent to expect incomplete responses rather than an error.

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 purpose before the usage guidance and the polling interval. No filler or restatement of the title.

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 return-value burden and does so by naming the fields an agent will receive, and it supplies the polling behavior needed to use a status tool correctly. Minor gap: nothing about what happens for an unknown or expired scan_id.

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 scan_id parameter already carries a pattern and a description naming fix_scan and list_my_scans as its source. The description restates the same provenance ('after fix_scan') without adding format or validation detail, 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?

States a specific verb and resource ('Check one book') and enumerates exactly what is returned: stage, pages done of the total, and the download link. The phrase 'one book' implicitly separates it from list_my_scans, so an agent can tell it apart from its siblings without opening a schema.

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?

Gives explicit trigger conditions ('after fix_scan or preview_scan', or 'when the user asks how their book is doing') plus a concrete polling cadence of 10 to 20 seconds. It stops short of an explicit exclusion such as 'use list_my_scans instead when checking several books', leaving that to inference.

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