wechat_search_messages

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It claims support for searching by sender, but the schema only exposes 'keyword' and 'limit', with no sender parameter, creating ambiguity about how to perform a sender search. The description also omits details like whether the search covers all conversations, pagination behavior, or read-only nature. This is a significant transparency gap for a search tool with no annotation support.

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, concise sentence with no wasted words. It is front-loaded with the core action ('search historical messages by keyword'). While it is brief, it is not verbose or redundant. However, its brevity may contribute to the lack of behavioral details, so it barely misses a 5 for perfect conciseness.

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?

With no output schema and no annotations, the description is the only source of context, but it leaves out critical information about return values, error handling, and operational scope (e.g., whether the search is global or per-conversation). The parameter count is small and the schema is clear, so the tool is not overly complex, but the description is too sparse to be considered complete for an agent to invoke it confidently.

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%, with both keyword and limit having Chinese descriptions. The description adds marginal value by mentioning searchable dimensions (text content, sender), but does not clarify how to specify the sender in the keyword parameter. Since the schema already defines the parameters clearly, the description contributes little beyond the baseline, though it does hint at keyword semantics that are not fully explicit.

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's function: searching historical message records by keyword. It distinguishes this from sibling tools like wechat_get_messages by explicitly focusing on keyword-based search, and further specifies it can search by text content and sender. This is an unambiguous 'search' verb with resource and scope, fully clarifying purpose.

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 the usage context: when you need to search historical messages by keyword, rather than simply retrieving messages. It establishes a clear context for use, though it does not explicitly name alternative tools or mention when not to use it. The presence of wechat_get_messages as a sibling provides implicit contrast, but the description could be stronger with explicit exclusions or alternatives.

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