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

Annotations already declare destructiveHint=true, so the description doesn't need to repeat that. It adds the useful nuance that the operation is recoverable ('still recoverable from the system trash'), which goes beyond the annotation. No contradiction with annotations.

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?

A single sentence, front-loaded with the usage condition and the key differentiator (recoverable). No wasted words, perfectly concise.

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 two-parameter operation with an output schema and annotations covering destructive behavior, the description is complete. It tells the agent exactly when to use the tool and what it does, and the output schema covers return details.

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%: both device and source are well documented in the schema. The description itself adds no extra parameter meaning beyond the schema, so baseline 3 applies.

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 ('move to trash') and resource ('file or directory'), and explicitly contrasts with permanent deletion via 'still recoverable from the system trash.' This distinguishes it from sibling tools like delete_path and delete_paths, which imply permanent removal.

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 gives a clear condition for use: when the user wants removal but recovery from trash. It implies that for permanent deletion, other tools like delete_path should be used, but does not explicitly name alternatives. This is clear context, though not an explicit exclusion.

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