eda_pcb_manufacture_data_get_manufacture_data

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

With no annotations provided, the description carries the full burden, and it discloses the single most important behavioral trait: it always throws an Error in non-private-deployment versions. It also states the return type (File | undefined). It does not describe whether the operation has side effects or what triggers undefined, but the failure-mode disclosure is genuinely valuable and beyond what structured fields would provide.

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 compact — a signature line, a short Chinese purpose, a remarks line, a note, and a returns line. No filler words. It front-loads the signature and purpose before the caveats. The only minor flaw is the mixed-language layout, but the content is efficiently organized.

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?

The critical constraint (private deployment only, always throws otherwise) is present and the return type is named. However, with no output schema and an empty args definition, the description leaves the agent without details on what 'manufacture file' actually contains, what conditions yield undefined, and what the args configuration requires. For a tool that aggregates all manufacture files, this is adequate but not complete.

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 100%, so the baseline is 3. The args parameter is entirely unspecified (items: {} with no type), and the description only hints that data comes from '前端一键导出制造文件弹窗的配置' (the front-end one-click export dialog config), which loosely maps to args but never documents what those arguments actually are. windowId is not addressed in the description at all. It neither compensates for nor worsens the schema.

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 ('导出制造文件' / export manufacture files) and resource, and ties it to the one-click export dialog feature, which helps distinguish it from the many per-format siblings (get_gerber_file, get_bom_file, etc.). However, it never explicitly frames itself as the combined/one-click export alternative to those format-specific tools, so sibling differentiation is implied rather than stated.

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 discloses the private-deployment-only constraint ('仅私有化部署版本有效...将始终 throw Error'), which is useful exclusion guidance. But it gives no when-to-use versus when-not-to-use guidance against the ~20 sibling get_*_file tools; an agent has to infer that this is the one-click combined export and must not be used for a single format. No alternative tools are named.

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