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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds useful non-obvious context explaining the heuristic behind flagging — a number 'appears in the documents, or behaves like staff.' It does not say whether these are pending suggestions, whether the list is exhaustive, or how results relate to the answering sibling.

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?

Two tight sentences with no filler, and the resource definition comes first followed by the operational rationale. The only cost is that the compressed, idiomatic phrasing of the first clause trades clarity for brevity.

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 one-optional-parameter read tool with no output schema, the description plus annotations cover enough to invoke it correctly. The main remaining gap is that the follow-up workflow — pairing a returned suggestion with answer_internal_number_suggestion — is left implicit, which matters in a 45-sibling surface.

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% and the single optional `brand` parameter is fully documented in-schema, including the cross-reference to `get_overview` brands[].slug. The description adds no parameter-level meaning, which is acceptable at this coverage level.

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 description identifies the resource well — numbers that look like the business's own branches or staff — which is genuinely distinguishing. But it never states the action: nothing says this lists/returns suggestions, and the opening phrase 'Numbers writing to the assistant' is grammatically ambiguous about who is doing what. An agent can infer retrieval from the name, not from the text.

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?

'Exclude them so the assistant stays out of those chats' gives a downstream rationale but not a when-to-use condition, prerequisite, or route to an alternative. The obvious sibling, answer_internal_number_suggestion, is never mentioned, so the agent must guess whether this tool also resolves/answers the suggestion or only surfaces it.

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