construir-perfil-maestro

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

With no annotations, the description carries the full burden and does well on the critical point: 'No guarda nada' makes clear this is a non-persisting drafting tool and that persistence is delegated to guardar-perfil-maestro. It also discloses input-dependent behaviour (PDF yields extracted text + schema + rules; URL-only yields export instructions). It does not mention file-size limits, supported PDF edge cases, or what happens with unexpected/mixed inputs, leaving some behavioural gaps.

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?

Front-loaded with the action and precondition, then branches by argument type and closes with the no-persistence caveat. Dense but every clause carries information; the multi-clause sentences are slightly heavy but not padded.

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?

Five optional parameters, no annotations and no output schema. The description covers the two main input paths and the non-persistence contract, which is what an agent most needs. It leaves the foto, texto and desde_portal parameters behaviourally undocumented and gives no indication of what a returned draft looks like structurally, so a small gap remains.

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, but the description adds meaning beyond the schema by explaining what each input path produces (PDF → extracted text, standard schema, assembly rules; linkedin_url alone → how to export the profile). It does not explain texto, foto, or desde_portal behaviourally, so it is not fully compensating.

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 and resource ('Crea el perfil maestro') plus a precise precondition ('cuando aún no existe'), and explicitly distinguishes the operation from the sibling guardar-perfil-maestro, which it names. An agent can tell it apart from the write-side sibling without opening either 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 explicit when-to-use (profile does not yet exist) and then branches guidance by input: with no arguments it says what to ask the user for; with a PDF it describes the derived output; with only a LinkedIn URL it explains the export path. It also names the follow-up tool and the condition for it ('tras la confirmación del usuario').

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