resolver_duda

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses the response shape (brief answer in voseo + source + confidence) and, importantly, the failure mode — it explicitly returns 'Sin fundamento en el manual' when nothing backs the answer. It also declares it does not read or touch business data. Not covered: latency, and what 'confianza' looks like in practice.

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 purpose, then output contract, then the negative boundary — a sensible ordering. The text is dense and slightly run-on (long parenthetical plus two clauses joined by semicolons), but no sentence is filler.

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 single-parameter, no-annotations, no-output-schema knowledge tool, the definition covers what it does, what it returns, its sourcing, and its out-of-scope boundary. Minor gaps remain around confidence semantics and how off-topic questions are handled beyond the 'sin fundamento' fallback.

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 value by scoping what counts as a valid question ('cómo se hace algo en la app', with the enumerated topics), which tells the agent how to phrase and constrain the free-text input rather than just passing raw chat text.

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: it answers USAGE questions about the Nortex app, and it enumerates concrete topic examples (vender por caja, códigos de barras, regalías, lotes, anulaciones). The closing line 'Solo conocimiento: no lee ni toca datos del negocio' cleanly separates it from every sibling tool, which are all business-data readers.

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 explicit: it is for 'cómo se hace algo en la app' questions, and the no-data-access clause functions as a clear when-not for anything involving live business records. It stops short of naming the alternative siblings (ventas_hoy, stock_producto, etc.), so the agent must infer the routing itself.

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