eda_sys_file_system_get_libraries_paths

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. The description does add meaningful behavioral context: it explicitly states the tool throws an Error in browser environments and throws when the external interaction permission is not enabled. It also mentions the return type (Array<string>). However, it doesn't disclose side effects (there appear to be none, which is implied by 'get'), performance implications, or what the paths look like. The error conditions are the most valuable behavioral disclosures and they are present, so a 3 is fair.

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 one-line purpose statement plus two numbered 'remarks' covering critical error conditions and a 'returns' line. Each sentence earns its place. The structure is front-loaded with the purpose then the operational constraints. It could be slightly tighter (the code signature is redundant with the name) but overall it's efficient and the critical usage conditions are clearly highlighted.

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 no-parameter getter tool, the description covers the essential operational constraints: offline-only, permission requirement, and return type. The input schema covers the wrapper parameters. However, the description doesn't clarify the shape/format of the returned paths (absolute vs relative, platform-specific formatting) or explain the 'args' parameter usage (whether it should be empty). Given the tool is simple and the schema is rich, this is adequate but not complete; a 3 reflects that an agent can call it correctly but may not fully understand the return value format.

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 input schema has 100% description coverage: 'args' is described as ordered JSON parameter array and 'windowId' as target EDA window ID. The tool actually takes no real parameters (the method signature shows no args — just the wrapper params args and windowId). The description doesn't add any parameter-level semantics beyond the schema, but with 100% schema coverage the baseline is 3. The 'args' array is generic and the description doesn't clarify what arguments go in it (it appears the underlying method takes none), which is a minor gap. Baseline 3 is appropriate.

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 the tool gets library directory paths (获取库目录路径) and includes the method signature. This is clear about the resource (library directories) and the action (get paths), though it doesn't explicitly differentiate from very similar siblings like get_projects_paths or get_documents_path. Given the name itself contains 'get_libraries_paths' and the description restates this, it's clear but relies somewhat on the name. A 4 is appropriate because the verb+resource is clear and the signature adds specificity; distinguishing from sibling path-getters is left to the name.

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 'remarks' section provides explicit when-to-use conditions: it only works in fully-offline clients and throws an Error in browser environments, and requires the extension's external interaction permission to be enabled or it will always throw. This is useful environment/scoping guidance. However, it doesn't mention when to prefer this tool over alternatives like eda_sys_file_system_get_projects_paths or eda_sys_file_system_get_documents_path, which are sibling tools with the same pattern. The usage guidance covers prerequisites but not alternative selection.

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