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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds genuinely non-obvious behavior: a payment gate, watermarked raster pages before payment, and that raw text is never returned pre-payment. That is meaningful disclosure beyond the structured fields, though it doesn't address rate limits or error/auth failure modes.

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?

Two sentences with no wasted words; the payment precondition is front-loaded and the negative constraint (raw text never returned) is a useful closing qualifier. The parenthetical phrasing ('and, for eligible letters, has it sent') is slightly convoluted but still compact.

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 correctly carries the return-value burden by naming the full text and dashboard link. It explains the gating behavior that determines whether anything usable comes back, leaving only minor gaps around failure responses.

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%, so both case_id and access_token are already documented as values returned by start_document. The description adds no additional syntax, format, or coupling detail for either parameter, which is the expected baseline when the schema does the work.

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 outcome (the full text of each drafted document plus the dashboard approval link) tied to a clear resource, so an agent knows this reads drafted output rather than metadata. It does not explicitly contrast itself with the closest siblings (prepare_protected_draft, start_document), so it falls 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?

Gives a hard precondition — 'After genuine payment only' — which is real when-to-use guidance, and implies the pre-payment state is a when-not-to-use case. It stops short of naming an alternative tool for the pre-payment situation, so no explicit routing is provided.

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