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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds substantial context on top: the response opens with a link line, the JSON begins with «url», each figure carries a source and an inventory level (Primaria/Secundaria*/Supuesto), and the agent is told to cite 'Fuente: El Puente' and to state that this is orientative and not financial advice. It also bounds editorial behavior ('no recomiendes productos financieros, fondos ni entidades').

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 and every sentence carries information, but the description is a single very dense paragraph that interleaves return format, provenance levels, branding, pricing, disclaimers and editorial policy. Slight restructuring would improve scannability, though little is outright waste.

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 return-shape burden and does so: it explains the leading link line, the «url» key, and that each parameter comes with its source and inventory level. It also covers the required citation and the disclaimer an agent must reproduce, so nothing essential to correct invocation and presentation is missing.

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% and the single optional 'tema' parameter is fully documented in the schema ('Sin él, devuelve todos'). The description never mentions 'tema' by name, though its enumeration of covered figures loosely maps to the enum values, adding only marginal meaning beyond the schema. Baseline 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 los parámetros de 2026 que usa la calculadora') and then enumerates exactly which figures are returned (pensión máxima, bases de cotización, integración de lagunas, edad ordinaria, IRPF, IPREM, etc.). It also names the sibling tools calcular_pension and coste_del_puente in describing how the returned «url» behaves, so an agent can tell this apart from a calculation tool.

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 tool is positioned as the reference source for 2026 rules, with calcular_pension/coste_del_puente given as the places where the URL opens a filled plan. There is no explicit 'use this when the user asks for the rules/figures, not a personal estimate' exclusion, nor any prerequisite statement. The citation and disclaimer instructions are behavioral policy, not selection guidance.

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