私信会话 / 聊天记录

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the ascending-time ordering and the mode-dependent return shape, which are useful, but says nothing about pagination, cursors, rate limits, or how limit behaves per mode.

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?

A single sentence with two balanced clauses, zero redundancy, and the conditional trigger front-loaded so an agent can branch immediately without reading the schema.

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?

For a two-parameter read tool with full schema coverage and safety annotations, the definition covers what it needs: both modes and the ordering of results. It stops short of describing pagination or the fields present in each return shape, which matters slightly since there is no output schema.

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 description coverage is 100% and the schema already documents both parameters, including talker_id's '不传则列出会话' semantics. The description largely restates that behavior; the only extra signal is the ascending order of the message mode, so baseline 3 is appropriate.

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 states a specific verb+resource pair (list DM conversations / read chat history) and makes the two operating modes explicit via the talker_id condition. It is clear but never distinguishes itself from the sibling write tool send_message, which sits right next to it in the toolset.

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 gives clear, actionable context: use without talker_id to list conversations, with talker_id to read that user's history. No exclusions, prerequisites, or alternative-tool routing are offered, so it falls just short of the 5 bar.

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