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

Annotations already declare write/destructive/openWorld/non-idempotent, so the bar is lower, and the description still adds real substance: the per-call cap, that numbers with a leading single 0 inherit the list's calling code, that duplicates and invalid numbers are counted rather than added, and that nothing is sent. Missing auth/permission notes, but the mutation profile is well covered.

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?

Dense, front-loaded single passage with no filler: write marker first, then target identifier, then input modes, then edge-case semantics, then the 'sends nothing' reassurance. Every clause carries information an agent would otherwise have to guess.

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 4-parameter mutation tool with no output schema, the description covers inputs, limits, normalization, and error-ish handling (duplicates/invalid counted). What is left implicit is the return payload and whether the counted duplicates/invalid values are surfaced in the response, the one detail an agent calling this blindly might still want.

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 0%, so the description carries the full burden and mostly does: it explains `items` element shapes (bare number or {msisdn, vars}), the only meaningful `source` value, and that the list is addressed by id or uuid. It never states whether exactly one of `wp_list_id`/`wp_list_uuid` is required, leaving a real ambiguity given zero required parameters.

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: adding numbers to a saved list identified by `wp_list_id` or `wp_list_uuid`. The channel is only implied by the `wp_list_*` parameter names rather than stated explicitly, so the agent must infer this is the WhatsApp variant among the add_*_list_members siblings, but the parameter names disambiguate well enough.

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 a clear operating branch: either supply `items` or use `source="customers"` to pull all customers with a phone. It also states the 10000-per-call limit. It does not point to alternatives (e.g., remove_wp_list_members to remove, list_wp_list_members to read), but the when-to-use context is unambiguous.

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