Buscando palabras clave

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

With no annotations, the description carries the full burden and does disclose the return shape ({'ok','q','sugerencias','nota'}) and the cap of up to 50 suggestions. It doesn't discuss failure modes or rate limits, but for a read-only suggestion endpoint there is little behavioral surface to disclose.

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 definition is front-loaded with purpose and integration, then Args and Returns blocks. Every element is relevant, and since no output schema exists, documenting the return dict earns its place rather than being redundant.

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-annotation, no-output-schema tool, the description covers purpose, usage in the broader search workflow, the parameter contract, and the return shape. It is nearly self-sufficient; only edge behaviors (empty results, error note semantics) are left unstated.

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 0%, so the description must compensate for the single parameter, and it does: it defines q as initial text, specifies the 1+ character minimum, and gives concrete examples ('indemnizacion', 'reivindicacion'). This adds real meaning beyond the bare 'Q: string' in the schema.

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 names the specific resource (keyword autocomplete suggestions) and states the scope of what it returns. It distinguishes itself by naming the sibling tools (buscar_resoluciones, buscar_laudos) whose keyword values it feeds, though the operating verb is implicit rather than a clean verb+resource phrasing.

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?

It clearly explains the workflow context: the exact returned values are used as 'palabra_clave' in buscar_resoluciones and buscar_laudos, which tells the agent to call this before those searches. It lacks an explicit when-not-to-use clause, but the integration guidance is unambiguous.

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