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

Annotations already declare readOnly/idempotent/non-destructive, and the description confirms 'Read-only.' Beyond that it discloses the payload shape (evidencia with type, aliases, relations, facts; reason nullable) and the important behavioral note that 'distintas' is permanent. It does not cover ordering or how pendientes is computed, which is minor.

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-loads purpose, then differentiation, then decision semantics, then args and return shape — a sensible order with no filler sentences. The decision-vocabulary block is slightly long but each label earns its place by preventing misuse.

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, the description supplies the return shape (dudas list with id, entity_a, entity_b, reason, evidencia plus pendientes) and the full read-decide loop. Nothing an agent needs to call this and act on the result is missing.

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 carry the parameter: it does, giving the meaning and the 1-20 bound for limit. The schema default of 5 is not mentioned, and no behavior is described for out-of-range values, keeping it short of a 5.

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 ('return pairs of entities that may be the same and that NEXUS could not decide') and immediately names the sibling it is not (get_next_question), including the distinguishing property por_usuario=False. An agent can pick this over the sibling without opening either schema.

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?

Explicitly says these doubts are for the agent to decide rather than to ask the user, points to retrieve_memories for context, and routes decisions to decide_merge_proposal with a precise semantic mapping of fusionar/distintas/posponer. When-to-use and what-to-do-next are both covered.

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