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

Beyond the readOnlyHint/idempotentHint/destructiveHint annotations, the description discloses the non-obvious truncation behavior: 'Nunca niega: recorta y lo declara' — the tool will not error or return empty when the requested window exceeds the free tier; it truncates and says so. It also adds the access-tier constraint (free last 30 days, deeper with Enterprise API key) and the data semantics (amplitude and median move independently). These behavioral traits are exactly what annotations do not carry.

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 and packs distinct value: purpose, conceptual rationale, access tiers, truncation behavior, param summary, and sibling routing. It is somewhat longer than strictly necessary — the rhetorical question and the risk-signal explanation make the same point in slightly different ways — but each remaining sentence earns its place with non-redundant information.

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 3-param, 0-required, no-output-schema tool, the description covers the non-obvious ground well: what the series represents (P10–P90 by category), the free/Enterprise access split, truncation behavior, and sibling routing. The main gap is the absence of any return-format detail (e.g., date granularity or whether mediana is included per row), which matters more because no output schema exists. This keeps it just shy of complete.

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% — the schema already documents dias (default 30, max 3650, truncation), api_key (Enterprise format and header alternative), and categoria (full list of accepted values). The description only restates 'Params: dias (default 30), categoria (opcional)' and ties dias to the free window, which the schema's truncation note already covers. The baseline of 3 applies since the schema does the heavy lifting.

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 verb+resource: 'Serie histórica de la BANDA observada (VR v1.0): cómo evolucionó el rango P10–P90 por categoría en el Mercado Agroganadero.' It names the exact metric (P10–P90 dispersion range over time) and explicitly differentiates from siblings by pointing to get_precios_hacienda for today's value and valuar_tropa for herd valuation. An agent can distinguish this tool from the 23 siblings without opening the 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?

The description opens with the exact question the tool answers ('¿Se está abriendo o cerrando la dispersión de precios?') and explains it is NOT for the point-price question ('Es la pregunta que el precio puntual NO puede contestar'). It closes with explicit alternatives — 'Valor de HOY → get_precios_hacienda; valuar una tropa → valuar_tropa' — and states the free vs Enterprise access condition. This is explicit when/when-not/alternatives routing.

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