Send buttons

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

Annotations only declare writability, open-world scope and non-idempotency; the description adds real behavioral detail beyond that: a quick reply comes back as a message.received of type button carrying button.id, a url button opens HTTPS, and WhatsApp suppresses the quick reply in the sender's own view while recipients can tap it. That last quirk is exactly the kind of non-obvious behavior an agent cannot get from annotations. It does not describe delivery failure modes or what the call returns, keeping it below 5.

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 sentences, front-loaded with purpose and constraint before the behavioral detail, with no filler. Slight density cost from inline backticked field names, but nothing is redundant or wasteful.

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 an 8-parameter outbound messaging tool with full schema coverage and no output schema, the description covers the two things that matter most: the button model and the reply/tap semantics. It leaves the mentions, idempotency and quote-reply behavior entirely to the schema, which is acceptable given complete parameter documentation but is the remaining gap.

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 description coverage is 100%, so every parameter including to, idempotencyKey and replyToMessageId is already documented in structured form. The description reinforces the id-vs-url choice and frames footer as optional small print, but adds little syntax or format detail the schema does not already carry. Baseline 3 is appropriate.

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?

The first sentence states a specific verb and resource with a hard constraint ('Send a message with 1 to 10 tappable buttons'), which cleanly separates it from send_text, send_media, send_poll and send_location without needing to name them. It then characterizes the two button flavors, so an agent knows exactly which capability it is choosing.

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?

Use case is implied by the resource: reach for this when the reply needs to be constrained to tappable options rather than free text. However there is no explicit routing guidance against send_text or send_poll, and no stated preconditions such as account requirements or when a link button is preferable to a quick reply.

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