exception_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. It discloses two behavioral traits: logs are automatically collected after connection and limited to 500 entries. However, it does not explicitly confirm whether the operation is read-only or whether it clears logs, though '获取' implies a read. Some useful context is added beyond the name.

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, front-loaded sentence in Chinese that conveys all essential information without redundancy. Every piece of content (purpose, connection requirement, limit) earns its place.

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 (no parameters, no output schema), the description is sufficiently complete for an agent to know what it does, when it can be invoked (after connection), and what to expect (up to 500 exception logs). The return type is implied by '获取' and the noun '日志'.

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?

The tool has zero parameters, so schema coverage is effectively 100%. Per the calibration guidelines, 0 params gets a baseline of 4. The description adds no parameter semantics, but none are needed.

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 retrieves exception logs from the mini-program runtime, using a specific verb ('获取') and resource ('异常日志'). It also adds distinctive details (auto-collection after connection, 500-entry limit) that help differentiate it from sibling tools like console_messages.

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 after connection (logs are automatically collected) and provides a context clue, but it does not explicitly state when to prefer this tool over alternatives like console_messages or clear_event_logs. No exclusions or alternative tools are mentioned, so the guidance is only implicit.

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