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

Annotations already declare a non-read-only, destructive, non-idempotent, open-world operation, but the description goes well beyond them: it names the exact HTTP-style outcomes (202/409/422), details template re-validation errors, explains paused-broadcast pending-recipient semantics, the restart-stuck `sending` state, and a concrete rate limit (10 requests/min per key shared with WhatsApp template endpoints). This is unusually rich behavioral disclosure.

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?

The purpose is front-loaded in the first sentence and every subsequent sentence carries real decision-relevant information (error codes, paused semantics, rate budget). The density of inline back-ticked state names makes it a heavier read than ideal, but there is little filler to cut.

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, the description covers the success response (202 with broadcast in `sending`), all failure branches, prerequisite states, side effects on pending recipients, and rate limits. An agent has everything needed to invoke and interpret the call correctly.

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 both agent_id and broadcast_id are fully documented in the schema itself. The description adds no syntax or format detail beyond what the schema provides, so the baseline of 3 for schema-covered parameters 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?

States a precise verb+resource+scope: 'Sends the template again to the recipients whose message failed.' It clearly distinguishes itself from the sibling `send_broadcast` by acting only on failed recipients of an existing broadcast, so an agent can route correctly without opening the 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?

Explicitly enumerates when retry is valid (broadcast finished, has failed recipients), when it is not (409 broadcast_still_sending, 422 invalid_request, paused-with-no-failed-recipient), and what to do instead (retry later, contact support). The paused-broadcast edge case and the alternative action are spelled out, leaving nothing to inference.

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