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

Beyond the annotations (which already cover read-only and idempotent safety), the description discloses important behavioral traits: truncation to the most recent points when the series exceeds max_puntos, and the escape hatch (full series in the linked CSV). This truncation rule is material and not visible in the schema. It does not describe the shape of returned points, keeping it from 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?

Purpose is front-loaded in the first clause, with coverage frequencies and truncation rationale following. It is dense but each element earns its place; the parenthetical of frequency history is long but informative rather than filler.

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, and while the description explains truncation and the CSV fallback, it does not describe the returned series format (e.g., timestamped points). Annotations cover safety, so the remaining gap is the return representation, which leaves it adequate but not 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 coverage is 75%, so most parameters are already documented (desde/hasta as optional dates, serie as the identifier). The description adds real value on max_puntos by explaining what happens on overflow, though it largely restates the default 104 and cap 520 already present in the schema. Baseline 3 fits a high-coverage schema doing most of the work.

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?

Names a specific resource (price series) and the selection criteria (by identifier, between two dates), which is clearly distinct from siblings like gasoleo_hoy or precio_ultimo that return a single current value. It does not explicitly name those alternatives, but the temporal-range framing makes the scope inferable.

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 implied rather than stated: the range/identifier framing signals 'use for historical lookups' versus the point-in-time siblings, and the frequency notes tell the agent what history is available. There is no explicit when-to-use, when-not, or named alternative, so it stays at implied guidance.

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