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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely useful behavioral context beyond that: the data is restricted to processes that already closed and to the last two years, and the output is a median and typical range. It does not discuss auth, latency, or sampling size, keeping it below a 5.

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?

Two sentences, front-loaded with what is returned and its scope, then the crucial framing caveat. No filler; every clause earns its place by constraining the data or clarifying the nature of the result.

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 what comes back, and it does — median and typical range by facet — while annotations cover the safety profile. It is essentially complete for invocation, though it omits how missing filters are combined or sample-size caveats.

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 rubro, objeto and region. The description restates the same filter axes (región, tipo, rubro) without adding format, default, or interaction details beyond what the schema provides, so the baseline of 3 applies.

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 ('devuelve cuánto se adjudicó frente al valor referencial'), plus the exact scope: closed Peruvian State processes in the last two years, broken down by región, tipo y rubro. An agent can tell this is a statistics lookup, not a search or listing tool like the buscar_* siblings.

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 closing sentence 'Es estadística descriptiva, no una recomendación de precio' sets expectations about the nature of the output, which implicitly tells the agent when this is appropriate (reference context, not a pricing decision). However, it never names an alternative sibling or states explicit when-to-use/when-not conditions, so usage remains largely implied.

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