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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds genuinely useful traits beyond that: oldest-first ordering, page-then-cursor paging, inclusion of topics with no prompts yet, and the topics_truncated partiality flag. It stops short of saying what a row looks like structurally beyond field naming, so it is solid rather than exceptional.

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 purpose, then a dense field/cohort inventory, then paging and alternatives. Almost no filler, though the row-field enumeration is packed enough to be slightly heavy on first read.

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?

There is no output schema, so the description carries the return-shape burden and does reasonably: it enumerates row fields, explains cohort categories, describes the topics list and its truncation flag, and details paging. The main residual gap is the exact envelope/pagination field naming (next_cursor vs the schema's cursor), which an agent narrows from context.

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 all six parameters are documented in the schema and the baseline is 3. The description does add meaning for cohort (core scored vs comparison naming a competitor, reported separately) and for active/audit status, but it does not explain the filters' interaction or the valid range of limit beyond what the schema says.

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?

Opens with a specific verb and resource ("List the prompts the project tracks") and immediately frames the scope as enumeration, not search or results. It names the distinguishing siblings (search, read_visibility_results) so the agent can tell it apart 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?

States when to reach for it ("before reading results or changing prompts") and explicitly routes the two most likely competing intents elsewhere: wording lookup goes to search, per-prompt engine answers go to read_visibility_results with the prompt_id. Downstream tools that consume the returned ids are also named.

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