photoshop_command_execute

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

The annotation marks destructiveHint as true, but the description does not warn about potential side effects or irreversibility. It mentions 'risk' and 'approval' checks, which hint at safety, but it does not explain that execution may modify state or have external consequences. Without describing behavior, the agent cannot foresee the impact. It does not contradict the annotation, but it fails to disclose the destructive nature.

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 a single sentence, concise and without redundant words. It front-loads the core action ('Execute a catalog command') and then lists checks. It is not overly verbose, but it is so terse that it sacrifices informative content. The structure is acceptable for the length, but the content is minimal.

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 tool with 6 parameters and zero schema coverage, the description is incomplete. It does not explain what 'catalog command' means, what the output schema might be, nor how the various optional parameters interact. Given the destructive hint, an agent needs to know about approval and idempotency safeguards. The description provides only a generic preview, leaving the agent with many unknowns.

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 0%, and the description provides no explanation of any parameter. It does not mention command_id, args, approval_token, idempotency_key, dialog_mode, or verification. The agent is left to infer semantics from names and enums, which is insufficient for correct invocation, especially for optional but important tokens like approval_token.

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 uses the specific verb 'execute' and targets a 'catalog command', which distinguishes it from siblings like photoshop_command_search and photoshop_command_describe. However, it does not define what a 'catalog command' is, though that may be established by related tools. It is not a tautology and gives a clear enough sense of purpose.

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?

There is no guidance on when to use this tool versus alternatives. It does not mention that approval may be required first, nor does it reference the approval flow or other prerequisites. The description only states that checks are performed but does not explain the conditions under which an agent should invoke this instead of other tools.

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