review_list

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

Annotations already cover read-only/idempotent, but the description adds substantial behavior beyond them: paragraph grouping and address, how adjacent delete+insert are collapsed into a single `replace` with `old`/`new`/both `ids`, what `totals` counts, and how the `author` filter narrows both changes and threads. Pagination is fully disclosed — roughly 8,000 bytes per reply, limit up to 1,000 paragraphs, continue via `cursor` set to `next`.

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?

Front-loaded with the core purpose and packed with distinct rules rather than filler. It leans on long, clause-chained sentences (the replace/insert/delete sentence and the ids sentence) that take a second read, which costs a little against 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 paged, filterable reader whose output schema exists, everything an agent needs is present: what one paragraph entry contains (address, current text, threads with id/author/date/quote/resolved/replies, changes), the aggregation in `totals`, the pagination contract, and which sibling tools consume the ids.

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%, so the baseline is 3; the description earns above that by explaining that `author` keeps that author's changes and the threads they wrote in — a semantic the schema's 'Only this author's' does not convey — and by tying `cursor` to the reply's `next` field. `limit` and `doc` add nothing past the schema.

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 ('Read a reviewed document') plus the exact scope: comments and tracked insertions/deletions grouped by paragraph in document order. It explicitly distinguishes itself from revision_list ('adds formatting, moves, table changes and notes') and from comment_list by covering both comments and changes in one pass.

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 concrete downstream routing: the returned ids feed revision.accept / revision.reject (both of a replace) and doc.batch comment.reply / comment.resolve, and revision_list is named as the alternative when formatting, moves, table changes or notes are needed. That is an explicit use-this/when-to-use-other pair, not an inference.

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