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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description layers on substantial behavior the annotations cannot express: a 10 req/min per-key rate limit counted separately from other calls, caching advice, and precise failure semantics — 404 not_found for a non-WhatsApp connection, 409 connection_inactive, 409 connection_needs_reconnection (retry won't help), and 503 meta_unavailable with retry-with-backoff. It also explains the per-item payload shape for building a later POST.

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-loaded and dense with useful detail — scope first, then payload shape, then rate limit, then error taxonomy. The only waste is the opening line, which merely restates the tool title verbatim before the real content begins.

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?

No output schema exists, and the description compensates by describing the return contents in detail: one item per language version, sorted, up to 100 items, each carrying body/header parameter keys in order, header format, and button index/value field. Combined with the complete error taxonomy, nothing needed to call it correctly is missing.

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?

Both parameters are fully described in the schema (100% coverage), so the baseline is a 3. The description adds meaning beyond the schema by tying `connection_id` to the concept of 'one of the agent's WhatsApp numbers' and by restating the 404 case for a connection that isn't a WhatsApp number in the tool's own semantic frame.

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 (list every template of one of the agent's WhatsApp numbers), plus scope details that separate it from siblings: live read from Meta, one item per language version, sorted by name then language, capped at 100. An agent can distinguish it from send_whatsapp_template or get_whatsapp_message_status 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 clear operational context: templates are read live from Meta, so 'keep the list, and read it again after your templates change,' and only `approved` templates can be sent (implying send_whatsapp_template is the routing target). It does not explicitly name any sibling tool as an alternative, so it stops short of full when/when-not routing.

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