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

Goes well beyond the readOnly/idempotent annotations: caps the window at 168 hours, discloses that an empty result is reported explicitly rather than silently, that each call returns a refreshed search_token, and that tokens expire after 30 days of disuse. Those are exactly the operational facts an agent needs for a scheduled polling loop.

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 return contract, then usage context, then token lifecycle. No filler and nothing repeated for its own sake.

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 and only three parameters, the description carries the return-value burden and does so adequately: it says what the results are, what happens when there are none, and that a token comes back. It stops short of describing the listing payload or result-size/pagination behavior, which is the main remaining gap.

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 window_hours bounds, default, enum values and the token's provenance are already documented in the schema. The description largely restates the 168-hour cap and the token source; the genuinely new facts (token refresh, 30-day expiry) are behavioral rather than parameter-level.

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 precise verb, resource and filter: return only listings *first seen* within window_hours for a given search_token. The word "only" plus the token-scoped scope cleanly separates it from search_listings, which is named as the source of the token.

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?

"Built for scheduled checks that the user sets up, for example daily or every few hours" gives clear usage context and implies this is a follow-up tool rather than an initial search. It routes implicitly to search_listings for token creation, but never states an explicit when-not-to-use condition (e.g. don't call this first, don't poll more often than X).

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