invert_selection

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

There are no annotations, so the description carries the full burden of behavioral disclosure and does little with it. It says nothing about what happens when nothing is selected, whether the operation is per-image and affects the active image only, or what the status dict contains beyond the bare "Returns status dict" remark. Mutation of editor selection state with zero disclosure of failure modes or side effects is a real gap.

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 definition is short and front-loaded: the action sentence comes first, then a small parameter block, then the return note. Nothing is padded, though the parameter section is essentially a restatement of the schema rather than earned content.

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 one-parameter selection mutation this is close to minimally viable: the core action is clear and the return type is at least mentioned. However, with no annotations, no output schema, and an image-editor context where selection state is conditional, the missing preconditions and side-effect notes leave the definition thinner than the tool's actual complexity warrants.

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% for the single parameter, so the description must compensate, but "Target image index (default 0)" merely restates the property name and the default already declared in the schema. It adds no information about how the index relates to the focused image or what happens if the index is invalid.

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 and resource ("Invert the current selection") and the parenthetical "select what is not selected" removes ambiguity about the operation's effect. It implicitly separates itself from select_all/select_none/invert_colors by naming the selection state, though it never explicitly contrasts with the very similarly named sibling invert_colors.

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?

No guidance on when to use this versus select_all, select_none, modify_selection, or invert_colors, all of which sit in the same sibling set. It also never states the prerequisite that an active selection should exist for the inversion to be meaningful, leaving the agent to infer preconditions.

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