construir-perfil-maestro

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

No annotations are supplied, so the description carries the full burden, and it does: it declares the tool has no side effects ("No guarda nada"), names the sibling that performs the write, and describes the response contents (extracted text, standard schema, JSON rules) despite there being no output schema. For a non-persisting draft tool, that covers the traits an agent actually needs.

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?

Four sentences, purpose front-loaded, and every sentence carries information: what it creates, what to ask for, what each input yields, and what it does not do. No filler or restated metadata.

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 five optional params, no annotations, and no output schema, the definition covers the critical facts: no persistence, the save sibling, and the shape of the returned material. It remains silent on the texto and desde_portal paths and on failure modes (invalid PDF, unavailable LinkedIn URL), which keeps it from being fully complete.

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 structured field documentation already carries the baseline. The description adds conditional behavior for cv_pdf and linkedin_url (and mentions the photo in the no-args flow), but says nothing about how the texto or desde_portal parameters behave or how inputs combine — a partial supplement rather than full compensation.

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") and adds a scoping clause ("cuando aún no existe") that makes it distinguishable at a glance from ver-perfil-maestro, actualizar-perfil, and guardar-perfil-maestro. An agent can tell what it produces (a draft/schema) versus what it persists without opening the 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 the use condition (only when the master profile doesn't exist yet), the behavior for each input mode ("Con un PDF...", "con solo la URL..."), the zero-argument path, and explicitly routes saving to guardar-perfil-maestro after user confirmation. That is a real when-to-use / when-not / alternative mapping rather than implied guidance.

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