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

Behavioral transparency is high. The description discloses that the tool is a paid function ('Es una función de pago') and requires authentication ('Requiere iniciar sesión'), which are key behavioral aspects not covered by annotations. It also reveals the confirmation process, that email notifications are sent, and that NIF lookup is performed for company names. These details go beyond the minimal destructiveHint annotation to give a full picture of the tool's 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 well-organized, front-loading the purpose and then providing differentiation, parameter details, and critical workflow steps. However, it is slightly verbose, with some redundancy such as repeating 'por cada nombre se busca su NIF' which is already in the schema. The structure is clear and every sentence serves a purpose, but tightening could improve conciseness.

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 lacking an output schema, the description is remarkably complete for the tool's complexity. It covers the use case, alternative tools, the exact confirmation workflow, cost implications, authentication requirements, and the nature of the alerts (email on public money movements). This provides sufficient context for an agent to select and invoke the tool correctly without additional information.

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 has 100% parameter coverage with detailed descriptions for both 'empresas' and 'confirmar'. The description repeats the NIF search detail and the purpose of the confirmar parameter, but adds little new semantic meaning beyond what the schema provides. The baseline of 3 is appropriate since the schema does the heavy lifting and the description does not introduce additional parameter nuances.

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's function: 'Crea una vigilancia de una o varias EMPRESAS concretas' and explains it notifies by email on public money movements. It explicitly distinguishes from the sibling tool crear_alerta by stating 'Para vigilar un TEMA (un sector o tipo de ayuda) usa crear_alerta; esta es para empresas con nombre y apellidos.' This provides a specific verb, resource, and differentiation from similar tools.

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 provides explicit when-to-use guidance by naming the alternative tool for themes (crear_alerta) and specifying this tool is for specific companies. It also gives detailed usage instructions for the two-step confirmation flow: 'llama primero con confirmar=false (por defecto) para mostrar el usuario qué empresas se van a vigilar' and 'vuelve con confirmar=true' after confirmation. Additionally, it notes the tool is paid and requires login, setting clear conditions for use.

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