List chats

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful details about the output structure (compact rows, fields parameter), aligning with annotations without contradiction.

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 concise, uses two short sentences, and front-loads the core purpose (recent conversations) followed by output details and a tip about the 'fields' parameter. No fluff or redundancy.

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?

Given the simple list operation and lack of an output schema, the description provides sufficient context (sort order, returned fields, field filtering) for an agent to understand the tool's functionality and expected results.

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?

The schema provides complete descriptions for all four parameters (kind, limit, fields, unread_only), so the description adds no additional parameter semantics. Per the rule, a baseline score of 3 applies when schema coverage is 100%.

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 clearly states the tool lists recent conversations with a compact row per chat, including fields like id, name, kind, unread count, and preview. This distinguishes it from siblings like get_chat (single chat) and search (query-based).

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 description implies usage for retrieving recent chats but does not explicitly compare with alternatives like search or get_chat, nor state when not to use this tool. The 'newest first' ordering provides some context, but explicit guidance is absent.

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