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

Annotations already declare readOnly, idempotent, closed-world and non-destructive behavior, so the description only needs to add context. It does add the return-content contract (summaries and links, no message texts) and implies a pending-reply indicator, but says nothing about page size or how many chats come back per call.

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 short sentences with no filler, and the most decision-relevant detail (no message texts) is placed last but clearly. The opening phrase is a little too clever to be maximally front-loaded.

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, so the description must characterize the response – it does, naming summaries, links and the absence of message bodies. Pagination behavior is left to the schema, which covers it adequately.

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?

Only one optional parameter, and the schema documents it fully (100% coverage) including the example format and the null-means-last-page convention. The description adds nothing about the cursor, so the schema carries this dimension.

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 second sentence defines the resource precisely: the person's chats returned as short summaries plus links, explicitly excluding message texts. The list semantics come from the name rather than the description, and no sibling (e.g. chat_summary) is named to sharpen the boundary.

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?

"Chats and who waits for whom" hints at the use case – seeing which chats await your reply – but the description never states when to pick this over chat_summary or send_message, and offers no exclusions or prerequisites.

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