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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description is free to add what they cannot: the calculation basis (real traded lots, matched category and day), that the indicator is proprietary, and that the response is an already-drafted citation ready to publish, plus a public reference page. It stops short of describing response structure or whether the quote is localized, but the added context is substantial.

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 core definition is front-loaded and clear, but the rhetorical sentence about the band widening and the full English duplication inflate the length without adding selection-relevant information. Useful facts (decile definition, same-category/same-day matching, ready-to-publish output) are mixed with promotional framing.

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 carries the burden of explaining return values; it says a drafted citation is returned but not its shape, language of output, or what happens when a week has no data. For a one-parameter read-only indicator this is workable, but a mutation-free, simple tool still leaves the response contract partially implicit.

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?

Only one optional parameter exists and schema coverage is 100%, with the default ('el último dato') documented in the schema itself, so the baseline applies. The description does not add anything about the fecha cutoff format or how historical weeks behave, but nothing is missing that the agent needs.

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 states a specific metric with its exact scope: the gap between the bottom and top deciles for the same category on the same day, computed over lots actually traded at the Mercado Agroganadero, updated weekly. It also explicitly contrasts itself with average-publishing reference prices, so an agent can tell it apart from livestock_prices or price_dispersion_history without opening a 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?

Usage is only implied ('esta semana', default last data point). There is no explicit when-to-use statement, no named alternative such as price_dispersion_history, and no guidance on when the weekly band is the wrong choice versus a plain price query.

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