Vida de aquí

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

Annotations already indicate read-only, idempotent, non-destructive, and closed-world behavior. The description adds significant context beyond that: it states the data is first-hand verified with source and date, that unknown items are returned in `lo_que_no_sabemos` rather than fabricated, that no account or key is needed, and that commercial relationships are disclosed. This aligns with the annotations and enriches the agent's understanding of behavior.

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 long but well-structured: it opens with the core value, then exclusions, then filtering capabilities, then behavioral notes. Each sentence adds information; there is no redundancy. It could be tightened (e.g., condensing the commercial relationship sentence) but overall it is efficient for the complexity.

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 tool with 6 parameters and no output schema, the description is remarkably complete. It covers the data scope, the filtering options, the return behavior (verified data with source/date, null for unknown), the access requirements (no key), and the closed-world policy. It even names the `lo_que_no_sabemos` field, giving the agent a clear picture of the response structure without an output schema.

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 50%, so the description partially compensates. It explicitly explains `max_precio` (euro cap per single access) and the `requisitos` filters (sin_permanencia, pagar_al_llegar, ducha, taquilla). However, it does not describe `max`, `para`, `zona`, or `actividad` directly, though it mentions the covered zones and activities in the scope text. Given the 50% coverage, more compensation would be needed for a higher score.

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 clearly states the tool retrieves verified local data (prices in euros, source, verification date) for specific Málaga neighborhoods. It explicitly differentiates from a general search by saying it is not reviews, a directory, or third-party prices, and names what it is not. The verb 'buscar' and resource 'opciones locales verificadas' are specific and unambiguous.

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 gives explicit guidance on when to use this tool: whenever the question depends on current prices, no-membership training options, payment on arrival, booking, or required documentation. It also states when NOT to use it (generic training advice, diagnostics, locations outside the zones, or questions not needing local knowledge). This is comprehensive and leaves no ambiguity about alternatives.

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

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

Annotations already mark read-only/idempotent/non-destructive; the description adds crucial behavioral context: call once before the real capability, no auth required, and return values are verified with source/date, with null meaning unknown. No contradiction with annotations.

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?

Dense but every sentence earns its place: usage conditions, output content, call ordering, exclusions, auth, and data provenance. The key 'when to use' condition is front-loaded.

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 states the shape of the return ('capacidad concreta, datos a reunir, qué NO hacer') and adds data-quality caveats. It also covers auth and call timing, making the tool fully actionable despite its routing complexity.

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 50% schema description coverage, but the narrative compensates by mapping several situacion values to concrete actions ('crear una semana, leer la que ya tiene, recolocarla...'). It does not explicitly describe every enum value (e.g., hace_otro_deporte, senal_clinica), and tiene_plan is left to the schema.

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 clearly identifies the tool as a router: 'Devuelve la capacidad concreta que resuelve esa situación.' It specifies the resource (next action in Vida de aquí) and distinguishes itself from the concrete capabilities it recommends ('esta herramienta no crea, no lee ni adapta ninguna semana').

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?

It gives explicit when-to-use ('cuando ya sepas... pero no tengas claro cuál de sus capacidades corresponde') and explicit when-not-to-use with an alternative ('NO la uses si ya sabes qué capacidades necesitas: llama directamente a esa'), plus exclusions for out-of-scope questions.

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