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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description reinforces the destructive behavior explicitly ("it REPLACES the one saved before"). It goes well beyond annotations with privacy guarantees ("the videos never leave their computer"), the required user-confirmation step, and a domain gotcha about measurement not detecting sound effects mixed under voice.

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?

Opening sentence front-loads the action and the replacement warning, which is the right priority. The text is long and mixes instruction with shell commands, but nearly every sentence carries operational or safety value; only the worked examples for look fields are slightly verbose.

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 complex mutation tool with nested objects, 8 parameters, and no output schema, the description covers prerequisites, how to source each required argument, privacy constraints, a confirmation checkpoint, and a known measurement limitation. Nothing an agent needs in order to call it correctly is missing.

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 coverage is 88%, so the baseline would be 3, but the description adds substantial meaning: pass version/videos/measured/summary exactly as printed, never pass perVideo because it holds local paths, and guidance on what to write in each look field with concrete examples. This materially changes how an agent fills the arguments.

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?

States a specific verb (Save) and resource (this workspace's edit style) plus the critical scope fact that it REPLACES the prior style. An agent can distinguish it from get_edit_style, delete_edit_style, add_style_examples, and update_brand_style from the description alone.

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?

Gives an explicit gating condition: "Only when the user asked for their style to be learned (or to change it)." It also prescribes the preparatory workflow (run style measure, look at stills, confirm with the user) and the "show the user before saving" precondition. It stops short of naming sibling alternatives such as add_style_examples or import_style_from_link, so 4 rather than 5.

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