Send message with buttons

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

Annotations already flag destructive=true, openWorld=true and idempotent=false, but the description adds far more: the non-official WhatsApp Web/QR channel, the ban/restriction risk from unsolicited or repetitive messages, that sends cannot be reliably un-sent, and that a timeout must be reconciled against chat history before retrying. That is exactly the operational context the annotations cannot express.

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?

Purpose and the 3-button limit are front-loaded, then safety constraints follow in a logical order. It is dense with useful rules rather than filler, though the risk/ban paragraph and the button-type enumeration together make it long enough that the core 'what it does' line gets diluted.

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 destructive, open-world mutation with 7 params and no output schema, the definition covers safety, opt-in, instance selection (via schema) and retry semantics thoroughly. The one real gap is that it never says what comes back (e.g. a message id usable with edit_message, delete_message or react_to_message), which an agent needs to continue a workflow.

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 the baseline is 3; the description earns above that by explaining which nested fields pair with which button type (reply = text+id, link = text+url, call = text+phone, copy = text+copy code) and by adding the cross-parameter rule that button kinds should not be mixed. The "up to 3" restates maxItems, but the type-to-field mapping is genuine value.

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 and resource ("Sends a text message with up to 3 buttons") and immediately enumerates the four button kinds, which cleanly separates it from send_text, send_media and send_poll. An agent can pick the right send tool without opening any schema.

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 concrete use cases ("menus, confirmations and calls to action"), an explicit constraint ("keep one kind per message"), an opt-in precondition, and a do-not-retry-after-timeout rule. It even explains why the constraint exists (the "open on your phone" notice), so the guidance is actionable rather than advisory.

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