analyze_wechat_chat

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses a key side effect: it can write raw JSON, analysis JSON, and Markdown to the local workspace. It also clarifies the read scope (paged, up to 5000 messages) and the analysis pipeline. It does not mention overwriting behavior or whether source messages are modified, but the main side effect is explicitly surfaced.

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 that front-loads the core action (paginated read + analysis) and then adds output details. No filler or redundant restatement; every clause contributes meaningful information about purpose, behavior, or outputs.

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 complex tool with 9 parameters, no output schema, and 0% schema description coverage, the description is incomplete. It does not explain time-range filtering, cursor parameters, the exact structure of the analysis outputs, how output_dir is used (file naming, overwrite), or what the tool returns. An agent would likely need to ask follow-up questions to invoke it correctly.

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 several parameters implicitly: '最多5000' maps to limit, '分页' maps to offset/page_size, '指定会话' maps to session_id, and '写入本地工作区' maps to output_dir. However, start_time, end_time, after_local_id, and after_timestamp are entirely unexplained, leaving significant gaps for a 9-parameter tool.

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 and resource: '分页读取最多5000条指定会话消息' (paginated read of up to 5000 session messages), then enumerates distinct analysis actions (multi-label classification, risk/asset extraction, evidence indexing) and output-writing behavior. This clearly differentiates it from sibling read-only tools like get_recent_messages or search_messages, which only retrieve messages without analyzing or writing artifacts.

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 provides clear context: this tool is for reading a specified session's messages, applying analysis, and writing outputs to a local workspace. It implies when to use it (when analysis, risk/asset extraction, or evidence indexing is needed) but does not explicitly name alternatives or state when-not-to-use conditions, so it falls short of a 5.

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