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 does substantial work: it enumerates what each result returns (speedup DECLARADO by the source plus citation, primary papers, public implementations, and whether Rosetta measured it). Critically, it flags the epistemic caveat that the speedup is declared rather than measured, which changes how the agent should report results. It omits pagination, empty-result behavior, and whether the search is substring or semantic.

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?

Three sentences, front-loaded with the verb, corpus, and size, followed by return payload and then the selecting use case. No filler, no restatement of the tool name, and the most decision-relevant facts (scope limit of 60 entries, declared-speedup caveat) appear early.

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 no output schema and no annotations, the description covers the essential ground: what corpus, what it matches against, what results contain, and when to reach for it. Remaining gaps (result limits, behavior on no match, free-text vs. structured matching) are minor for a read-only catalog lookup.

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 both parameters are already documented in the schema, establishing a baseline of 3. The description adds one piece of real meaning: 'consulta' matches by name OR by the problem attacked, which the schema's example list alone does not make explicit. It adds nothing about 'categoria' beyond the schema's enumerated values.

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 ("Busca") tied to a named, bounded resource ("archivador de algoritmos cuánticos", 60 entradas en 4 categorías) and specifies the two match fields: nombre or problema atacado. The scope is quantified, so the agent knows exactly what corpus is searched and what dimensions the query covers.

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?

Provides an explicit triggering use case in quoted form: responder "¿existe un algoritmo cuántico para X y hay evidencia?". This tells the agent the question shape that selects this tool. It stops short of naming an alternative (e.g., buscar_evidencia) or stating when NOT to use it, so it is clear context without exclusions.

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