message.history

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly discloses the pagination-to-the-end behavior ('翻页到底'), which is a meaningful trait beyond the schema's limit_per_page parameter. However, it does not mention other behaviors like result ordering, read-only nature, or potential performance implications.

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 a single, compact sentence with the primary action front-loaded and the pagination behavior added as a parenthetical. There is no filler or redundant information.

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 tool's simplicity (two flat parameters, no nested objects) and the presence of an output schema, the description covers the essential action, target conversation, and pagination-to-end behavior. It lacks extended context like when to use or what the return shape is, but the output schema handles return details, and the description is sufficient for basic invocation.

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 0%, so the description must compensate. It explains the 'cid' parameter by referring to the '指定 cid 会话' (specified cid conversation), giving it semantic content. However, it does not explain 'limit_per_page' beyond the schema's default, leaving one of two parameters effectively undocumented in both schema and description.

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 uses a specific verb '拉取' (fetch) and a clear resource '历史消息' (history messages) for a specified 'cid' conversation, and adds '翻页到底' (paginate to the end) to define its scope. This clearly differentiates it from siblings like message.send, message.watch, and message.list-chats.

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 by stating what the tool does—fetching history for a cid—but does not explicitly mention when to use it instead of alternatives, nor any exclusions or context such as 'use this when you need full history'. Sibling names provide clues, but the description itself offers no explicit routing.

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