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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds significant behavioral context: the credit cost (1 credit, plus extra for optional fields), the conditional behavior for person CUITs, and the list of purchasable additional fields with their individual credit costs. This goes well beyond the annotations, though it omits potential error cases (e.g., invalid CUIT format or unavailable data).

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?

The description is front-loaded with the main purpose and lists contents in a single, well-organized paragraph. It is relatively long due to the enumeration of data categories and credit details, but each clause serves a purpose (what data, cost, person case). It could be slightly more concise by grouping the field list, but the structure is logical and efficient overall.

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 tool with no output schema, the description provides a comprehensive overview of the returned data categories and the credit model. It explains the optional fields and the person fallback, which are essential for correct usage. It does not specify the exact response structure or error handling, but given the absence of an output schema and the breadth of data, the description is sufficiently complete to guide an agent.

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?

The input schema already provides complete descriptions for both parameters (cuit and campos), including format and the list of available fields with credit costs. Schema coverage is 100%, so the baseline is 3. The description adds a concrete example (campos=beneficiarios) and reinforces the credit behavior, but this is marginal value over the schema and does not substantially improve understanding.

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?

The description clearly states the tool's purpose: it returns a complete file of an Argentine company by CUIT, listing the specific categories of information (registral identification, activity, directors, partners, corporate acts, BCRA credit situation, rejected checks, foreign trade, contracts, sanctions). It also distinguishes the person-CUIT case, directing to a person file, which differentiates it from the sibling ficha_persona. The verb 'devuelve' (returns) and resource 'ficha de empresa' are explicit and unambiguous.

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 implicitly defines when to use the tool: when you need a company file by CUIT. It explicitly handles the person case by stating that if the CUIT belongs to a person, it returns the person file (ficha: persona), which effectively routes the agent to the correct behavior. However, it does not name alternative tools (like ficha_persona) as a recommended fallback, nor does it state when not to use this tool, leaving the selection partially to inference.

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