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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly warns not to invent contact data, explains why the business needs it, and instructs the agent to offer a telephone fallback if the user declines. It also covers optional persona behavior and describes the return payload (folio, assigned person, address, map link, arrival lead time). While it does not discuss failure modes or side effects beyond creation, the provided behavioral guidance is substantial and valuable.

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 longer than average but well structured with a clear summary, a required-fields list, and separately labeled notes for contacto_cliente and persona. It front-loads the core purpose and then adds necessary behavioral nuance. Some repetition occurs around the contact requirement, but each section serves a distinct purpose and the length is justified by the need to prevent data fabrication and misrouting.

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 7 parameters, no schema descriptions, and no annotations, this description is highly complete. It covers required and optional inputs, format expectations, sensitive data-handling rules, and return values. The output schema may exist, but the description still usefully summarizes what the tool returns. An agent has enough context to invoke this tool correctly in a booking conversation.

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 0%, so the description must compensate, and it does thoroughly. It clarifies negocio as id or name, gives format for fecha (AAAA-MM-DD), provides an example for hora, explains contacto_cliente as the attendee's phone or WhatsApp, and explains the optional persona parameter in detail. All seven parameters receive meaningful semantic guidance beyond their bare schema definitions.

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 opens with a clear, specific statement: 'Crea una reserva en un negocio.' It also names the object being created, lists required inputs, and distinguishes itself naturally from sibling tools like cancelar_reserva and consultar_reserva by focusing on the creation action. An agent can immediately identify this as the booking-creation 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 explains when to call the tool by specifying required fields and even guides behavior around obtaining contacto_cliente and handling the optional persona field. It references ver_servicios for staff names, giving useful cross-tool context. It does not explicitly contrast with sibling tools or state when not to use the tool, but the usage context is clear and actionable.

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