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

With no annotations, the description carries the burden and does disclose key traits: it reads the service's own database (implying a safe read), and it is 'not metered' so there is no cost concern. It does not spell out pagination behavior or how results behave when filters match nothing, so it is strong but not exhaustive.

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 core action, then the routing rule, then the ranking capability. No filler and no repetition of schema text.

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?

Covers purpose, return fields, invocation ordering, ranking semantics and cost model for a five-parameter, zero-required search tool with no output schema. Only minor gaps remain, such as pagination/limit behavior and whether multiple filters are ANDed.

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 schema already documents all five parameters, giving a baseline of 3. The description earns above baseline by demonstrating the interaction of two parameters in a real query pattern, which the enum list alone does not convey.

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 ('Find hotels by name, destination or brand') and enumerates what each result carries (RoomExpert score, slug, page). It also positions itself against the sibling tools by declaring 'every other tool takes one [slug]', so an agent can immediately tell this is the entry-point search versus get_hotel/get_rates.

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 an explicit calling rule — 'Call this first whenever you do not already have a slug' — and states the precondition that every other tool requires a slug. A concrete ranked-search example ('quietest rooms in Tokyo' = destination 'tokyo', sort_by_axis 'noise') removes ambiguity about combining filters.

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