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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the bar is lower. The description does add real value by disclosing that the message is logged into the contact's conversation and that Contact/Conversa are created automatically when missing — a concrete side effect. It omits the WhatsApp Business constraints (message window / template requirement) and delivery-failure behavior, which matter for an outbound messaging 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?

Three compact sentences: action, format constraint, side effect — logically ordered and front-loaded. No filler, though the format constraint partly duplicates the phone parameter's own description.

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?

There is no output schema, so the description should ideally say what comes back (message id, status) or whether failure modes are reported. For a destructive, open-world outbound action it covers the creation side effect but leaves delivery/authorization behavior and the template-vs-free-text decision unaddressed.

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 coverage is 100%, so all three parameters are already documented in the schema, including the same international-format example. The description's format note ('sem espaços ou sinais') is a mild reinforcement but adds no syntax beyond the schema. It says nothing about the unusual optional 'numero' parameter that selects the sending account.

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?

Specific verb + resource ('Envia uma mensagem de texto via WhatsApp') plus the provider resolution rule (Meta or GupShup) and the recording side effect. 'Mensagem de texto' implicitly separates it from send_whatsapp_template, but no sibling is named, so an agent must infer that distinction.

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 never states when to prefer this over send_whatsapp_template, schedule_whatsapp_message, or send_sms, all of which sit in the sibling list and overlap heavily. Only a formatting precondition ('formato internacional sem espaços ou sinais') is given; no exclusions, no prerequisites about opt-in or the WhatsApp 24-hour session window.

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