run_es_companies_search

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

No annotations are provided, so the description carries the disclosure burden. It usefully adds the cost model ('2 point per returned record') and enumerates the fields returned, which is valuable with no output schema. However, it omits any note on auth/permissions, rate limits, or pagination behavior, so coverage is only partial.

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?

Two sentences, front-loaded with the verb and data source. The field enumeration is compact and the cost note is a short standalone sentence. No 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?

With no output schema, listing the returned fields is the right move, and the cost note is helpful. But the description is silent on pagination semantics (start_page, max_items exist in the schema) and on when this tool is the correct choice, leaving gaps for an agent navigating a large registry-tool family.

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 baseline is 3. The description meaningfully exceeds that by expanding the required 'keyword' parameter's semantics: the schema describes it only as 'Company name', whereas the description states it accepts name, brand, or NIF. That is a genuine clarification beyond structured data.

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?

Specific verb+resource: 'Search the Spain company registry' names both the action and the exact data source (Registro Mercantil, Registradores de España). It even enumerates the returned fields, so the agent knows what data comes back. It does not, however, differentiate itself from the sibling run_es_companies or the many other run_XX_companies_search tools beyond the country 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?

The description implies a search use case ('by company name, brand or NIF') but never states when to use this versus run_es_companies (the non-search sibling) or any other registry tool. No exclusions, prerequisites, or routing guidance are given, leaving the agent to infer selection.

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