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

Annotations already declare non-readonly, destructive, idempotent and open-world, so the safety profile is covered. The description adds real context beyond them: PilotControl, not the agent, delivers the message, the send is scoped to the single contact of that conversation, and the action is reversible via whatsapp_update_reminder. It says nothing about timezone handling, rejection of past times, or what the caller gets back.

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?

Three short sentences, front-loaded with the action, then the cancellation route, then the guardrail. Every sentence contributes and nothing is padded.

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 4-required-param mutation with no output schema and complete annotations, this is nearly sufficient: purpose, scope, confirmation gate and cancellation are all present. The remaining gap is timing semantics (timezone/reference for scheduled_for) and result expectations, which the description leaves entirely to the 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?

With schema coverage at 50%, the description carries partial load: it explains message as the text, conversation_ref as a WhatsApp chat reference and scheduled_for as "la hora indicada", which is mildly useful. It adds no format or timezone guidance for scheduled_for, the parameter most likely to be supplied incorrectly.

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 (programa) and resource (un mensaje a un contacto de un chat de WhatsApp) and ties the two key params to the schema. It distinguishes itself from the cancel path by naming whatsapp_update_reminder, though it never contrasts with whatsapp_send_message, the sibling an agent is most likely to confuse it with.

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?

"Úsala solo cuando el usuario lo pidió y confirmó el texto y la hora" gives an explicit precondition and effectively excludes speculative scheduling, and the cancel alternative is named. It stops short of spelling out what to do when the user has not yet confirmed (e.g. draft/confirm first) or which sibling sends immediately.

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