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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds the crucial undisclosed behavior: this is a monetization/pre-check tool whose output is a purchase link for a one-time paid download, not the data itself. That is exactly the kind of context annotations cannot convey. Gap: nothing is said about what happens if both optional parameters are omitted or if an id is malformed.

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 sentences, front-loaded with the most important caveat (no contact data is served here) and then the actual return value. Mostly waste-free, though 'con lo que trae' is vague filler that does not tell the agent what is included in the download.

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, the description carries the burden of describing returns and does so at a high level (per-company availability flag plus purchase link), and it documents the id format and its source tool. The remaining gaps are small: the vague 'con lo que trae' and no guidance for the case where both optional parameters are absent. Adequate for a two-parameter, read-only tool.

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 description coverage is 100%, so the schema already documents both parameters, the 25-id limit and the enum directories. The description adds only the origin hint (ids come from buscar_empresas) and a precedence hint ('o solo el directorio'), which largely duplicates the schema text. Baseline 3 applies when the schema does the heavy lifting.

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 concretely what the tool returns: it reports which of the requested companies have phones/emails and returns the paid-download purchase link for the corresponding directory. It also explicitly negates the assumption an agent would make from the title ('Cómo obtener teléfonos y correos') by saying the contact data is not delivered by this server. It does not explicitly contrast itself with ver_empresa, which is why it stops short of 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?

Signals the intended flow by saying ids are the 'directorio:slug' values coming from buscar_empresas, and that a bare directorio works as an alternative input. The 'no se entregan por este servidor' sentence functions as a negative-use warning that prevents an agent from calling it expecting contact data. It lacks an explicit statement of when to prefer it over ver_empresa or listar_directorios.

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