wechat_build

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

Annotations already declare destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds the return envelope {success, data, message, error_code?} but does not disclose real side effects: upload publishes a version, cache_clean irreversibly clears state, and most actions require a running IDE. That's useful framing but not full disclosure.

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?

Three short, front-loaded lines: capability, action list, return shape. There is minor redundancy in re-describing the return value when an output schema exists, and the action list is terse enough to be ambiguous, but nothing is padded.

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 13-field, multi-mode tool this is thin: no statement that the WeChat IDE must be open (or which sibling opens it), no per-action parameter expectations, and no warning about upload's external visibility. The existing output schema covers return values, so that omission is acceptable, but the operational preconditions are missing.

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 description restates the action enum with short glosses (compile=编译检查, upload=上传), which adds meaning beyond the bare enum whose schema description is only '操作类型'. However, it says nothing about the cross-field requirements (version/desc only for upload, cdp_port/cache_clean only for compile), leaving the 13 nested fields entirely to the schema. The reported schema coverage of 0% at the top level pushes this toward the baseline rather than above it.

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 names specific verbs (构建/预览/上传/npm 管理) and a concrete resource (小程序), and enumerates the five actions, so the agent can tell this is the build-and-release tool rather than execution or inspection. It does not explicitly contrast itself with siblings like wechat_ide or wechat_automator, which keeps it at 4.

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 action list implies when each mode applies (compile for checking, preview for previewing, upload for release), but there is no explicit 'use this when…, use X instead' guidance and no mention of prerequisites such as the IDE being open. Usage is inferable rather than stated.

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