Vida de aquí

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

The annotations already declare read-only, idempotent, non-destructive behavior, so the description does not need to restate safety. It goes beyond the annotations by disclosing that the tool returns verified options with source and freshness, that null fields mean unknown data, and that no account is required. This gives the agent useful behavioral expectations for a read-only search tool.

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 a long, dense block of prose with many comma-separated clauses, making it hard to parse quickly. While all content is relevant, it lacks bullet points or section breaks, and several ideas (e.g., access-pass details, exclusions) could be condensed. The most important usage guidance is front-loaded, but the overall structure is not concise.

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?

Despite the lack of an output schema, the description explains what the tool returns (verified options, sources, dates, synthesis, null-not-known), who can use it (no account), and what it is not for. It covers the main behavioral and usage context needed to call the tool correctly. Minor gaps remain, such as not describing the 'max' parameter, but the schema's enums and existing descriptions fill most of the void.

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?

The input schema already documents 3 of 6 parameters ('para', 'max_precio', 'requisitos'), leaving 'max', 'zona', and 'actividad' without descriptions. The tool description adds context around the visitor/access scenario and the zones, which helps interpret some parameters, but it does not systematically clarify each parameter. Since the schema coverage is 50%, the description only partially compensates for the gap.

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 local search-and-compare facility for specific fitness/health activities in defined neighborhoods, and it explicitly contrasts with generic-advice tools. It uses a specific verb (encuentra, compara, decide) and lists the exact activities and zones, making it easy to distinguish from the sibling 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?

The description gives explicit when-to-use scenarios (finding, comparing, or deciding where to train; also for day passes and drop-in access) and explicit when-not-to-use cases (generic training advice, diagnostics, non-local questions). It does not name the sibling tool 'recomendar_siguiente_accion' as the alternative, but the exclusion of generic advice effectively routes the agent away from it.

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.