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

Annotations already declare destructiveHint, openWorldHint and idempotentHint, so safety is partly covered. The description adds genuinely useful semantics about how idempotency works in practice ('un operation_id nuevo por mensaje; repetirlo no lo manda dos veces'), which tells the agent how to retry safely. It does not, however, spell out what a successful send returns or what failures look like.

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 tight sentences, front-loaded with the capability and followed by the usage constraint and the idempotency rule. The parenthetical '(files)' referencing the parameter name is slightly awkward but costs little.

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 indicate what comes back from a send (message id, delivery status, error cases); it is silent on that. Constraints and usage are well covered, so the gap is limited to the response side.

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?

At 60% schema coverage, the description contributes meaning beyond the schema: the country-code requirement for `to`, the file size and format limits, and the retry contract for `operation_id`. Some of the file constraints are duplicated in the nested schema description, so it is not maximally additive.

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 (send) plus the exact resource (text and/or a single JPEG/PNG/WebP image up to 5 MB) delivered through the brand's linked WhatsApp to a phone number with country code. It is clearly separable from campaign broadcast tools and from scheduling siblings.

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?

Gives an explicit precondition ('solo cuando el usuario pidió escribirle a esa persona y el texto está acordado') and an explicit exclusion with a named alternative ('nunca para mensajes masivos; para eso están las campañas'). The agent knows both when to call it and when to route elsewhere.

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