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

Annotations declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, and the description supplies the missing 'why': it 'uses one read and saves the result in the user's Puley history,' which explains the non-read-only flag and discloses a persistent side effect. It also discloses the silent default behavior for omitted dates ('assumed two weeks out for two nights and flagged'), which is exactly the kind of context annotations cannot convey.

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?

The purpose and return shape are front-loaded in the first clause, followed by compact per-parameter notes; nearly every phrase carries information. It is a dense run-on sentence rather than cleanly structured lines, which costs a little readability but not content.

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 an 8-parameter, no-output-schema, open-world search tool, the description covers result contents, defaults, filtering conventions, and the history-write side effect, so an agent could call it correctly without opening the schema. Remaining gaps are minor: guest count semantics, result volume/pagination, and any failure behavior when a site returns nothing.

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?

With schema description coverage at 0% across 8 parameters, the description carries the burden and largely meets it: it documents checkin/checkout format and default behavior, max_per_night units and the 0-means-any convention, sort values (price or rating), and sites values (airbnb, booking, default both). The gaps are adults (default 2) and currency (only indirectly referenced via 'in the currency'), so coverage is strong but not complete.

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?

The description names a specific verb and resource ('places to stay on Airbnb and Booking.com ... side by side') and enumerates the returned attributes (price for the dates and a night, rating, area, room, free cancellation, links). It does not, however, distinguish itself from near-neighbors in the sibling list such as find_homes or find_places, leaving an agent to guess which lodging tool to pick.

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?

Usage is implied rather than stated: an agent can infer this is the tool for accommodation searches with a place and dates. There is no explicit when-to-use/when-not framing and no routing guidance against find_homes, find_places, or find_cars, so the choice among travel-search siblings is left to inference.

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