select

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description does not contradict this. It adds real behavioral context beyond the annotations: the key constraint that 'the selection lives only in live mode or inside one run_lua call' is a non-obvious, operation-critical trait that structured fields do not convey.

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?

Two sentences, front-loaded with the core verb and action enumeration; the mode constraint is placed last as a caveat. The action list is long but every entry corresponds to a real enum value rather than generic filler, so it earns its space.

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?

No output schema exists, so return values need not be explained, but a 18-parameter tool at 33% coverage leaves several behaviorally significant params (mode, tolerance, contiguous, quantity, brush, frame, layer, sprite, backend) undefined in both schema and description. It is adequate given how well the action list is documented, but gaps remain for a tool of this complexity.

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 18 params and only 33% schema coverage, the description compensates by tying parameters to actions and clarifying semantics the schema cannot express: 'point' belongs to magic_wand, 'dx/dy' to move, 'file' accepts .msk or an image, and 'modifier' means expand/contract/border. Many params (mode, tolerance, contiguous, quantity, brush, frame, layer, sprite) remain undocumented, so it is not a 5.

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 ('Creates or changes the selection') and then enumerates all 15 supported actions, so an agent knows exactly what the tool covers. It does not differentiate from the sibling 'selection_edit', which appears to overlap in scope, so it falls short of a 5.

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 through the action list and the inline mapping of actions to parameters (e.g., 'magic_wand (point)', 'move (dx/dy)'), and the mode caveat scopes where it can run. But there is no explicit when-to-use vs. the similarly named 'selection_edit' sibling, leaving the agent to infer the boundary.

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