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

Adds real behavior beyond the annotations: the 24-hour reply window on Instagram/Facebook, the 5 MB single-image cap, the brand-account sending identity, and the retry contract (same operation_id on retries, new one per new request), which elaborates the idempotentHint. It does not explain why destructiveHint=true applies to a send operation, leaving that annotation unqualified.

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?

Front-loads what the tool sends and where, then layers constraints and workflow guidance. Each sentence carries usable information, though mixing composing rules ('hazlo corto... sin despedidas') with transport constraints makes it denser than strictly necessary.

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 mutation tool with no output schema, it covers channel eligibility, media limits, retry semantics and the multi-conversation confirmation flow. What remains unexplained is the return/result shape and the mismatch of the destructiveHint flag with an outbound message send.

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 already 75%, and the description still adds meaning: text and image are alternatives ('texto y/o imagen'), one image max with allowed MIME types and 5 MB cap, conversation_ref points to an existing conversation, and operation_id must be new per message. It adds the retry semantics beyond the schema's pattern description.

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 concrete verb+resource+scope: sends text and/or one JPEG/PNG/WebP image (max 5 MB) into an existing conversation from the brand account. Together with the Instagram/Facebook framing this distinguishes it from post tools and whatsapp_send_message, although it never explicitly contrasts with the closely named send_message_draft.

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 explicit when-to-use conditions and workflow: only when the user asked to reply, keep the reply short and in the user's language without farewells, and for multiple conversations show the replies first and wait for a single confirmation. The one missing piece is naming send_message_draft as the alternative when the user only wants a draft.

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