selection_edit

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

Annotations only declare readOnlyHint=false and destructiveHint=false, which is minimal for a tool whose enum includes delete, cut, and crop. The description adds useful per-action context (which parameters belong to which action). However, it says nothing about undoability, whether a selection is required, or how the clipboard is affected — important for this action set. Note a mild tension: 'delete'/'cut'/'crop' read as destructive while destructiveHint=false, though this is defensible if deletes are undoable.

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?

A single front-loaded sentence that begins with the core purpose ('Acts on the selection') before the action list. It is dense and slightly cramped as a run-on enumeration, but every clause adds a distinct action or parameter mapping rather than repeating structured data.

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 13-action, 11-parameter mutating tool with no output schema and thin annotations, the description covers the action surface and inline parameter hints but omits prerequisites (selection state), return/status behavior, and undo semantics. Reasonable but noticeably short of fully equipping an agent.

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 only 45%, so the description has to carry weight — and it partially does by mapping parameters to actions (paste takes optional x/y, stroke takes color, move_* takes dx/dy/wrap). It does not explain frame, layer, sprite, or backend, though those do carry their own schema descriptions. Adequate compensation without being thorough.

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 states a specific resource ('the selection') and enumerates every action the tool performs (copy, copy_merged, cut, paste, delete, fill, stroke, move_content/move_bounds, new_sprite, new_layer_via_copy/cut, crop). This makes the tool's scope clear and distinguishable from siblings like select, draw_shapes, or clipboard. It stops short of naming an alternative tool, so it is not 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?

There is no when-to-use guidance, no prerequisites (e.g. that a selection must exist first, or how it relates to select/clipboard), and no exclusions. The overlapping siblings (clipboard, copy_cel, crop_sprite, new_sprite, select) are never referenced, leaving the agent to infer routing entirely.

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