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

Annotations already declare non-destructive, open-world behavior, so the description's job is to add policy beyond that — and it does: 'comparison is not booking consent', 'Respect nextAction', and a rule that null/missing price fields mean unknown rather than free. The presentation contract (canonical url, price/currency/priceUnit, limitations) is useful even with an output schema present. The unexplained readOnlyHint=false on a search operation is a gap the description never addresses.

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?

Front-loaded with the trigger phrase, then scope limits, then geography strategy, then result presentation and consent rules — a sensible priority order. It is dense and slightly run-on in the middle (multiple geography/price rules packed into single sentences), but nothing is redundant filler.

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 17-parameter, zero-required, open-world search with an output schema, the description covers the hard parts: scope, location strategy, language support, currency dependency, and the non-consent semantics of surfacing options. Pagination/limit behavior and the interaction between date and availability checking are left entirely to the schema.

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 a solid 71%, and the description still adds disambiguation the schema cannot: provinceUuid means a whole province, area means a town, omitting geography means a national search. It also constrains 'query' to the need only, with place names carried in other fields. Parameters such as limit, date, delivery and partySize get no narrative treatment, so it's not a 5.

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 concrete verb+resource pair (find/compare services and providers) and bounds it geographically to Costa Rica, a province, a locality, or near a known customer location. Scope exclusions ('not general advice, job vacancies or services outside Costa Rica') further sharpen what this tool is. It does not name a sibling search tool (e.g. search_classes vs search_events) as a contrast point, which keeps it just under a 5.

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?

Explicit trigger ('Use when finding, comparing or booking...') plus explicit exclusions and a prerequisite routing rule ('For near me without a known location, ask for the area first'). It also tells the agent which geography field selects which scope. It stops short of naming alternative sibling tools for adjacent intents (classes, events, catalog browsing), so it's clear context without full alternatives coverage.

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