search_messages

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

Annotations only carry readOnlyHint and idempotentHint, so the description adds real value: result ordering (newest first), absence of rank or count, the pagination contract (cursor from 'next', continue while 'more' is true), and a prompt-injection warning that all returned names and text are third-party content. That warning is exactly the kind of safety context annotations cannot express.

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?

Three short sentences, front-loaded with the search semantics and ordering, then paging, then the safety note last. No redundant restatement of the name or schema fields.

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?

An output schema exists, so return shape need not be re-explained, yet the description still ties 'next' and 'more' to the paging loop and flags untrusted content. For a four-parameter, read-only search tool, nothing an agent needs 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?

Schema coverage is 100%, so baseline is 3, but the description still adds meaning: it clarifies that 'query' is conjunctive (every word must be present), that 'chat' restricts to one chat, and that 'cursor' is the previous response's 'next' value — a relationship the schema description only implies. Marginal but genuine surplus over the schema.

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 ('finds the messages'), the matching rule (contain every word of the query), the scope (all readable chats or one), and the ordering (newest first, without rank or count). An agent can immediately tell this apart from get_messages (fetch by id) or list_chats 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 concrete operating guidance: choose all chats or pass a chat id, and 'pass next as cursor while more is true' for paging. It stops short of explicitly saying when to prefer a sibling (e.g. get_messages for known message ids) or any exclusions, so it is clear context but not a full routing rule.

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