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

Annotations already declare read-only/idempotent/closed-world, and the description adds substantive behavior beyond them: default and maximum page sizes, the pagination loop contract, filter persistence across pages, ranking semantics (literal match, not popularity), no execution guarantee, and that external accounts are contracted separately. These are exactly the caveats an agent needs and none appear in the schema or annotations.

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 tightly packed sentences, front-loaded with the core purpose, then returns, then pagination contract, then caveats. There is no filler; if anything it is dense enough that the caveat sentence could be split for readability.

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?

An output schema exists, so return values need not be specified, yet the description still summarizes what comes back (author, link, requirements, compatibility; guides with identifiers). Combined with pagination rules and match caveats, an agent has everything needed to call the tool correctly and interpret results.

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 schema already documents every parameter including defaults, ranges and enum meanings. The description reinforces query matching semantics and pagination behavior but largely restates what the schema says (default 8, max 40, follow next_offset), so it adds little new per-parameter meaning.

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 ("Busca referencias de GitHub") and enumerates the filterable dimensions (texto, categoría, tipo) with the concrete kind enum values. It also distinguishes its output from sibling obtener_guia by explaining that guides carry the identifiers needed by that tool, so an agent can tell the two apart without opening schemas.

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 clear operating context: paginate via next_offset while has_more is true, keep filters stable across pages, and hand guide identifiers to obtener_guia. It also sets expectations (textual matching, not popularity ranking, no guaranteed execution). It stops short of stating explicit exclusions versus other siblings such as preparar_proyecto or the agente tools.

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