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

Annotations already declare readOnlyHint, idempotentHint, and closed-world scope, so the safety bar is lower. The description adds genuine behavioral context beyond them: it enumerates the specific failure classes it inspects and says each problem is returned with its fix. It doesn't say what is returned when nothing is wrong, but the added diagnostic scope is substantive.

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 with the user-facing question, then a compact enumeration of what is checked. The trailing "Read-only." merely restates readOnlyHint from the annotations rather than earning its place, a minor redundancy in an otherwise tight description.

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?

There is no output schema, so the description must convey return shape, and it does at a high level ("each problem with its fix"). It stops short of saying whether results are a flat list or grouped by category, and what a clean bill of health looks like — small gaps for a zero-parameter diagnostic.

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?

The tool takes zero parameters, which is the baseline-4 case. Nothing in the schema needs compensating for, and the description correctly implies a no-argument, account-wide check.

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?

Opens with the exact question the tool answers ("why are my messages failing / not arriving?") plus a concrete verb — checks the WhatsApp number connection, Meta's failure reasons, failed store automations, and unapproved templates. This clearly separates it from siblings like get_message_status (per-message status) or get_account_overview (general account health).

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?

The trigger condition is explicit and stated up front: use it for failing or non-arriving messages. However, it never names the alternative tools an agent might otherwise reach for (get_message_status, list_whatsapp_templates, get_bot_status) or states when not to use this one.

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