search_docs

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

With no annotations, the description carries the behavioral burden. It conveys that this is a search-like operation across the full learned corpus, which is useful, but it does not mention whether the operation is strictly read-only, how results are ordered or shaped, or whether pagination or auth constraints apply.

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?

One front-loaded sentence with no filler. It states the action, the resources being searched, the corpus scope, and the keyword mechanism in a compact and immediately parseable way.

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?

The input side is well covered by the schema, and the description gives the high-level behavior. But there is no output schema and no explanation of what results look like, and the boundary with sibling tools, especially query_api_knowledge, is not clarified.

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 parameters like query, tag, limit, and specId already have clear descriptions and examples. The description only reinforces the keyword-search mechanism without adding meaning beyond what the schema already 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 clearly identifies the verb ('Busca'), the resource types ('endpoints, operaciones, etiquetas y modelos de datos'), and the scope ('todas las especificaciones OpenAPI aprendidas'). It distinguishes itself from list_specs and the get_doc siblings, though it does not explicitly address possible overlap with query_api_knowledge.

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?

The usage context is implied: use this tool for keyword-based search across learned OpenAPI specifications. However, there are no explicit when-to-use or when-not-to-use conditions, and no sibling alternatives are named, so an agent has to infer differentiation.

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