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

Beyond the read-only annotations, the description discloses ordering, cursor pagination, the presence of tombstone_id and link_version, and the fact that a likely match is only a hint. It also warns that names and message text are untrusted customer-provided content that must not be treated as instructions, which is valuable safety context not expressed by annotations.

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 description is dense but front-loads the core definition and keeps every sentence relevant. It is somewhat packed with clauses, but there is no filler or repetition.

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?

The tool has an output schema, so return values need not be fully explained, yet the description still gives enough shape for an agent to understand what each row contains and how paging works. For a read-only list tool with three parameters, this is complete.

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 100%, so the baseline is 3, but the description adds useful meaning: include_linked_unnamed is explained in terms of contacts with generated labels, and cursor paging is tied to newest-first ordering. The limit parameter is not expanded beyond the schema, but the extra context is still meaningful.

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 gives a precise verb and resource: it lists hidden-number chats whose person is still unknown, defined as no contact row or only a provisional system-named stub. The @lid identifier and the distinction from linked-but-unnamed chats make it easy to separate from sibling list/search tools.

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?

It clearly defines the use case for the default call and explains that include_linked_unnamed broadens the result to chats linked to a contact with a system-generated name. It does not explicitly say when to use this instead of list_conversations or list_identity_candidates, but the scope is otherwise clear.

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