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

Annotations already establish read-only, idempotent and non-destructive behavior, yet the description adds real operational context: results are capped at 10 with a total count, rental prices are monthly, keywords match Spanish or English listing text, and returned links must be shown verbatim including query parameters. The only gap is the absence of any note on empty-result or no-match behavior.

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?

Lead sentence front-loads purpose and scope; subsequent sentences each add a distinct fact (return shape, location flexibility, rental units, keywords semantics, link handling). The long parenthetical place-name list and the return-value sentence sit slightly heavy against an output schema that already documents results.

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, all-optional search tool with an output schema, the description covers the ambiguities an agent would otherwise get wrong: how to resolve place names, what the result cap means, monthly rent pricing, and how to present links. Nothing essential to calling it correctly is missing.

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 76%, so the schema already documents most fields; the description still adds meaning the schema lacks — location accepts place names in any language or spelling at municipality, district or urbanisation level, and keywords searches Spanish or English listing text rather than titles. It adds nothing about deal/sort/bedrooms, which are already well covered by the schema.

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 (searches) and resource (live EVS catalogue of homes for sale, long-term rentals, new builds) plus exact geographic scope (Málaga province / Costa del Sol). It also clarifies what the tool returns (match count, up to 10 listings, search_url), which lets an agent distinguish it from get_property and list_locations without opening any schema.

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?

Explicitly routes the agent to list_locations for place names and explains that omitting location searches the whole province, and describes when to use keywords vs structured filters. It stops short of saying when to prefer get_property for a single listing or when not to use this tool, so it is clear context without full exclusions.

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