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

Annotations already declare it a safe read (readOnlyHint true, destructiveHint false), and the description adds the behavioral layer the annotations cannot: a 1-credit base cost, per-field surcharges, the rule that add-ons are billed only when data returns, creditos_cobrados and campos_sin_cargo in the response, and the free re-request within 5 minutes of the same query. It also discloses result caps (20 most recent acts, up to 20 directors, eventos_total / dirigentes_total) and that directorio_al.fecha may come back null.

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?

Purpose is front-loaded in the first clause and the pricing/limit details follow in a logical order. It is a dense single paragraph with many parentheticals, which makes some rules (directorio vigente vs sindicatura, the ChatGPT exception) harder to scan than a short bulleted structure would be, but almost every sentence carries decision-relevant information.

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 complex, multi-registry tool with no output schema, the description supplies what the agent needs to call it correctly and interpret the answer: costs, charge/no-charge rules, truncation caps with totals, the persona_id handoff to ficha_persona, and the null-directorate case. Nothing material for correct invocation 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 already 100%, so a 3 would be baseline; the description earns above that by tying campos to billing behavior (each extra field only charged if it returns data, with campos_sin_cargo reported) and by explaining that detalle=completo is free if requested within 5 minutes of the same consulta. It also explains the semantics of the directorio vigente / directorio_al date indirectly. Cost numbers themselves are largely repeated from the schema, which keeps this from 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 specific verb+resource (full company dossier by CUIT) and enumerates exactly which registries are covered: registral identification, ARCA-declared activity, directors/shareholders, Boletín Oficial corporate acts, BCRA credit standing, rejected cheques, foreign trade, public contracts and sanctions. It also explicitly separates itself from ficha_persona (person records) and notes the ChatGPT caveat, so an agent can pick it over siblings 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?

Gives clear conditional guidance: use campos=beneficiarios / campos=presentaciones_igj only when those extras are needed and budgeted, and use detalle=completo inside the 5-minute window when the full text is required. It routes person lookups to ficha_persona and clarifies the ChatGPT path via persona_id. It does not explicitly contrast with search siblings like buscar_empresas or buscar_dirigentes, so the boundary with those is left to inference.

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