modify_selection

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

No annotations are supplied, so the description carries the full behavioral burden. It notes that amount is ignored for sharpen and that a status dict is returned, but it omits prerequisite conditions (must a selection exist? what happens if none?), whether the operation is undoable, and whether it mutates the image canvas state.

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 summary sentence is front-loaded with the actions, followed by a compact parameter breakdown. Every line contributes information and there is no filler, though the trailing 'Returns status dict.' is minimal enough to be borderline padding.

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 3-parameter mutation tool with no annotations and no output schema, the description covers parameters adequately but leaves out prerequisite state, failure modes, and mutability/undo semantics. It is sufficient to attempt a call but not to predict its behavior reliably.

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 schema description coverage at 0%, the description does the needed work: it enumerates the accepted operation strings, explains that amount is a pixel radius for grow/shrink/feather/border and ignored for sharpen, and clarifies the default for image_index. This compensates well for the bare schema, though it could say what amount means for border specifically.

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 resource ('the current selection') and enumerates the five operations it performs, which lets an agent distinguish it from select_* and invert_selection siblings. It stops short of explicitly naming the boundary with those siblings, but the operation list is concrete and unambiguous.

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?

Usage is implied by the operation names and the phrase 'current selection', so an agent can infer this applies only when a selection exists. However, there is no explicit when-to-use guidance, no statement of prerequisites (an active selection is required for grow/shrink/etc.), and no routing to alternatives like invert_selection or crop_to_selection.

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