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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description usefully adds behavioral detail beyond them: the per-plant return fields, that inactive plants are flagged in SENASA, and the result cap (default 10, max 30). It does not mention pagination or error behavior, keeping it out of the top band.

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-loaded with the resource and selectors, with the return fields and the exclusion follow. The Spanish/English duplication adds length, but each clause (requirements, limit, exclusions) carries distinct information, so waste is limited.

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?

There is no output schema, so the description carries the return-value burden — and it does, enumerating name, province, matrícula, CUIT, ciclo and the inactive flag, plus the result cap. Nothing an agent needs to call this search tool correctly 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?

With 100% schema coverage the baseline is 3, but the description adds meaning beyond the schema: it states that query and provincia are alternatives where one suffices, and it documents the max limit of 30 that the schema only partly conveys (schema says default 10 only). This is incremental value over the structured fields.

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+resource: a directory of SENASA/MAGYP-licensed meat plants and slaughterhouses searchable by name, tax ID (CUIT) or province. It explicitly carves itself away from price and slaughter-volume tools ('No da precios ni faena — es directorio'), so an agent can distinguish it from siblings like livestock_prices or value_cattle_lot.

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 invocation conditions: 'Requiere query (nombre/CUIT) o provincia (una alcanza)' — at least one selector is needed — and a when-not ('No da precios ni faena'). It stops short of naming a sibling alternative, but the context and exclusions are explicit.

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