Remove AI watermarks from one file

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

The description adds real behavioral context beyond the annotations: the source is never overwritten, a cleaned copy is written beside it as <name>_clean, and mode=all degrades gracefully when extras or hardware are unavailable. It is consistent with readOnlyHint=false and destructiveHint=false, though it says nothing about permissions, runtime cost, or failure modes.

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 sentences, front-loaded with the core action, then mode semantics, then the non-destructive output guarantee. Dense but every sentence carries information; the mode clause is long and could be split for easier scanning.

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?

Given no output schema, the description supplies the essential return information (a cleaned copy at a predictable path, source untouched) and flags the conditional nature of mode=all. An agent has enough to call it correctly, with the main gap being inter-tool routing and error conditions.

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?

With 67% schema coverage, the description meaningfully compensates: it explains what each enum value of mode actually does, including the image-only restriction on 'all', and it documents the default output naming that the schema leaves unstated. Only the interaction between an explicit output path and the default naming is left implicit.

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 opens with a specific verb+resource ('Write a cleaned copy of an image or video') that is far clearer than the bare tool name 'remove', and it scopes the input to user-generated or edited media. It does not, however, distinguish itself from the siblings identify and batch, so an agent can't route purely from this text.

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?

Mode selection is well specified: metadata for lossless stripping, visible when a known AI label must also go, and all for the additional image-only scrub with an explicit capability caveat. What's missing is any guidance on when to reach for this tool versus calling identify first or batch for multiple files.

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