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

With no annotations provided, the description carries the full transparency burden. It discloses that files are moved to a recycle bin (not permanently deleted) and are recoverable for 30 days via web, plus the per-ID result return. This goes beyond a generic 'delete' statement, though it does not mention permission requirements or rate limits.

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 extremely concise: two short sentences. The first sentence states the core purpose and the recycle-bin behavior; the second adds operational details (one-by-one, failure isolation, per-ID results). No wasted words, and critical information is front-loaded.

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 simple one-parameter batch deletion tool, the description covers key aspects: purpose, recycle-bin behavior, recoverability window, partial failure semantics, and return format. Without an output schema, it still explains what the agent can expect. It doesn't mention the 100-item limit in prose, but that's already in the schema, so completeness is solid.

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 already provides full coverage for the sole parameter 'file_ids', including the note that they can be obtained via list_files and a max of 100. The description adds minimal parameter-specific meaning, only reinforcing that each ID is processed individually. Baseline 3 is appropriate given the high schema coverage.

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's purpose: '批量删除文件' (batch delete files), with specific details about the operation (moving to recycle bin). It distinguishes itself from sibling tools like delete_file (singular) by emphasizing '批量' (batch) and from folder-deletion tools by specifying '文件' (files).

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 usage context: it deletes one by one, and a single failure doesn't affect the rest, which implies it's suitable for batch operations where partial resilience matters. However, it does not explicitly compare to delete_file for single deletions or state when not to use it.

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