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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: it discloses the fallback behavior when a category lacks sufficient lot basis, explicitly promises not to invent a range, and reveals the pricing/quota model (free with daily cap, paid via x402 otherwise). It also states the methodology URL. This is meaningful behavioral disclosure beyond the 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?

The description is dense but well-structured: it front-loads the core purpose with a relatable example, then covers the output, fallback behavior, methodology link, pricing, and parameters. It's longer than ideal, but every sentence carries information an agent needs. The parameter list at the end is a slight redundancy with the schema, but it's compact and useful.

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?

For a valuation tool with no output schema, the description does a good job of explaining what the response contains: P10, median, P90, lot count, head count, USD totals (blue and official), and a dated source. It also covers the fallback behavior and pricing. The only minor gap is that it doesn't specify the exact response format or units beyond USD, but the description is otherwise complete for an agent to call it correctly.

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 all four parameters. The description adds value by explaining the optionality semantics: kg_promedio defaults to the typical sale weight of the category, and provincia is optional with the national MAG reference as fallback. It also clarifies that categoria is a MAG category. This goes beyond the schema's terse descriptions.

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 opens with a concrete, relatable example ('¿Cuánto valen 350 novillos en Formosa?') and then states a specific verb+resource: it values a cattle lot using the MAG observed price band (P10, median, P90), with supporting lot counts, head counts, USD totals, and a dated source. It clearly distinguishes itself from sibling tools like get_precios_hacienda or get_precios_detallados by focusing on whole-lot valuation with a confidence band rather than raw price lookup.

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 description explicitly explains when to use this tool (to value a tropa/lot) and what it does when data is insufficient (falls back to national MAG reference and declares it, never invents a range). It also gives clear pricing/usage context: free with a daily quota per origin, otherwise US$0.05 in USDC via x402. It doesn't explicitly name sibling alternatives, but the use case is so specific that the when-to-use is unambiguous.

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