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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the payload mirrors the person's confirm screen, carries the person's confirmation state, and may be incomplete while processing (complete: false), which tells the agent to re-call rather than treat the result as final. It stops short of describing scoping or failure behavior for a missing/unauthorized document.

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 sentences, front-loaded with the payload description, then the polling rule, then the handoff to confirm_policy_document. The first sentence is dense with a long parenthetical field list, which is justified because there is no output schema, but the phrasing 'as PolicyVera's own confirm screen shows it' is slightly indirect in a definition meant for an agent.

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 enumerating the extracted fields and the confirmation state, plus the asynchronous completion behavior. The only real gaps are what happens when processing fails or the documentId is unknown, which are secondary for a read-only single-parameter tool.

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 documentId parameter already documents its own default (newest policy document on the person's profile, the file get_upload_link took). The description adds no meaning about documentId itself and does not restate the default, so it neither compensates nor regresses — the 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 states a specific resource (the extracted read of an uploaded document) and enumerates its contents (carrier, policy number, premium, dates, deductible, coverage lines, people, home, cars), which lets an agent distinguish it from confirm_policy_document and get_upload_link. It is phrased as a noun phrase ('The read of an uploaded document as PolicyVera's own confirm screen shows it') rather than a verb, so the action is implied rather than stated, but the purpose is unambiguous.

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 gives a concrete polling rule — when the result has complete: false, a later call returns the finished read — and points to confirm_policy_document as the tool that records the person's confirmation. It does not explain how it relates to other document-listing siblings such as my_documents or get_my_document, so routing guidance is clear for the closest alternatives but not exhaustive.

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