Search chats

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds real behavioral detail beyond that: AND-semantics across query words, prefix and accent normalization, result ordering (title matches first, then newest), and that the best-matching message is quoted in results.

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 but front-loaded: the search action, then the matching rules, then ordering, then the result shape. Every clause carries information, though the single run-on sentence packs the ordering and return details together in a way that is slightly hard to parse.

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?

No output schema exists, and the description compensates by describing the return contents (chat id, quoted best-matching message) and ordering. For a 6-parameter search tool that is nearly complete; only ordering stability across large result sets and the effect of the filter parameters on ranking go unaddressed.

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; the description earns above baseline by explaining the matching semantics of the required 'query' parameter (word-splitting, prefix expansion, accent handling) that the schema's one-line 'The words to look for' does not convey. The optional tag/since/until/platform/limit filters are left entirely to 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 ('Find the user's saved conversations') and goes further to define what a match means: every query word present in title or messages, prefix matching, accent-insensitive. This clearly separates it from list_chats (enumeration) and read_chat (fetch by id).

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 clear — use this when looking for chats that 'mention something' by keyword — and the description routes the follow-up step to read_chat via the returned id. It never explicitly contrasts itself with list_chats (browse) or recent_topics, so the sibling differentiation is implied rather than stated.

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