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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description does not need to repeat that. It adds meaningful behavioral context: the data comes from NPPES crossed with Census, the ordering is based on a stated risk formula, and the output is deliberately not alphabetical. The exact 'casi cero' threshold is undefined, but this is a minor gap.

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 with no wasted words. The core output and ordering rule are front-loaded, followed by data provenance and a uniqueness claim. Every sentence contributes to the agent's understanding.

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 read-only, two-parameter list tool, the description gives the output domain, the ordering logic, the data source, and the uniqueness of the dataset. Even without an output schema, an agent can infer the response is an ordered list of municipios. The main missing detail is the precise threshold for 'casi cero', but that does not prevent correct invocation.

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 both 'especialidad' and 'limite' are already documented with clear semantics. The description reinforces that 'especialidad' is the core filter and that the result is a ranked set of municipios, but it adds no parameter-level detail beyond what the schema provides.

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 states the exact resource ('Municipios de Puerto Rico con cero o casi cero proveedores de una especialidad médica') and immediately adds a distinctive behavioral detail: ordering by 'riesgo real' rather than alphabetically. It also claims to be the only dataset of this kind for Puerto Rico, which differentiates it from sibling tools.

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?

Usage context is implied: an agent can infer this is for analyzing medical supply gaps by specialty in Puerto Rico. However, the description does not explicitly compare it to siblings like buscar_medico or directorio_plan_medico, and it gives no conditions for when not to use it.

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