krita_transform_canvas

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

The annotations already mark the tool as destructive and idempotent, but the description adds valuable context: the 8192 per side/16 MP bound, the coordinate semantics for resize, rejection of unrelated fields and locked/animated nodes, and the instruction to reuse operation_id. These go well beyond the structured hints and help the agent predict side effects and constraints.

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 description is four dense sentences with no filler. Each sentence delivers actionable information: scope, per-action requirements, coordinate semantics, and rejection/idempotency behavior. It is short enough to scan quickly while covering the most important operational details.

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?

Given the tool's complexity (five action modes, 11 parameters, no output schema), the description covers per-action parameter requirements, size bounds, coordinate semantics, failure conditions, and idempotency. The main gap is that it does not fully explain what 'Reuse operation_id' means in practice or how the result of the operation is retrieved, though sibling operation tools partially address that context.

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%, so the description carries the full burden for parameter understanding. It successfully maps each action to the required parameters and clarifies that filter is optional for scale. It also explains the nontrivial resize coordinate behavior. The standard context parameters (instance_id, document_id) are not explained, but they are common across the sibling tools, and 'Reuse operation_id' offers at least a hint about the operation lifecycle.

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 and resource: 'Transform the entire document'. It enumerates the five supported actions (crop, resize, scale, rotate, flip), and the phrase 'entire document' distinguishes it from sibling krita_transform_layer, which targets a single layer. This leaves no ambiguity about what the tool operates on.

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?

The description gives explicit per-action requirements: crop/resize need x,y,width,height; scale needs width,height and optional filter; rotate needs degrees; flip needs axis. It also states rejection behavior for unrelated fields and locked/animated nodes. It does not explicitly name an alternative tool for layer-level transforms, but the 'entire document' scope makes the boundary clear enough.

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