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

With no annotations, the description carries the full burden and does most of it well: it discloses upsert semantics (repeat calls update), the per-account/per-listing uniqueness constraint, that the review becomes publicly visible and is labeled agent-submitted, and that an unauthenticated call returns sign-in instructions rather than failing opaquely. Missing only finer points like moderation/delay or whether a review can be withdrawn.

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 tight sentences, front-loaded with the purpose, then the uniqueness/update rule, then the auth requirement. The auth sentence slightly restates the title's "sign-in required" but adds the useful hint about how to obtain instructions.

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 zero-parameter, no-output-schema tool, the description covers the critical unknowns — auth path, side effect visibility, and idempotent update behavior. The remaining gap is the argument shape, since the schema declares no properties at all and the description only describes them narratively.

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?

The schema is empty (zero properties), so the description is the only source of input semantics, and it does supply the rating range (1-5) and the optionality of the note. However, it never names the actual field keys or how to encode the rating versus the note, leaving an agent to guess the argument shape for a tool that evidently accepts data.

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?

Names a specific verb and resource ("leave a review on a listing") and spells out the payload conceptually (1-5 star rating, optional note). It is unmistakably distinct from every sibling in the set (search_listings, get_listing, submit_listing), so an agent can route here without ambiguity.

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 the key usage condition — one review per account per listing, calling again updates the existing one — which resolves the create-vs-update question an agent would otherwise guess at. It also flags the sign-in prerequisite up front, though it doesn't explicitly warn against using it for non-review submissions (that is submit_listing).

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