krita_fill_layer

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

Annotations already mark the operation destructive and non-read-only, and the description adds substantial behavior beyond that: it specifies source-over vs destination-out compositing, per-mode parameter requirements (erase forbids color; gradient needs end_color/start/end; flood needs point), selection masking, and the exact flood-matching algorithm. It also discloses the lack of undo guarantee and advises reusing operation_id, which is consistent with the idempotentHint. No contradiction with annotations.

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 a single dense paragraph that front-loads the core behavior before detailing mode-specific requirements and limitations. Every sentence adds non-redundant information, and there is no filler or repetition of schema titles.

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 an 11-parameter schema with zero property descriptions, no output schema, and a destructive multi-mode operation, the description covers the critical operational facts: modes and their required parameters, target layer type, size limit, selection mask, and undo behavior. The only minor omission is naming a specific sibling as a fallback, but the constraint set is sufficient for an agent to decide when to invoke this tool.

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 must carry the semantic load, and it largely does: it maps each 'kind' value to its required parameters (color for non-erase, end_color/start/end for linear_gradient, point for flood) and clarifies that opacity/selection coverage drive erase intensity. The only parameters left implicit are the generic instance_id/document_id/node_id identifiers, whose roles are inferable from their names and the phrase 'paint layer.'

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 action ('fill or erase') on a precisely bounded resource ('simple RGBA/U8/sRGB paint layer') plus key constraints (1 MP, current-selection mask). The mode enumeration and 'No brush simulation' clause clearly separate it from the sibling paint/path tools. This goes well beyond a restatement of the name.

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 conveys clear usage context by listing constraints: it applies only to simple RGBA/U8/sRGB layers, is limited to 1 MP, and is masked by the current selection. It also states exclusions ('No brush simulation, tolerance, or guaranteed undo'), indicating when the tool is not appropriate. However, it never names a specific alternative tool, so the routing guidance is implicit rather than explicit.

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