adjust_image

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

With no annotations, the description carries the full burden. It does disclose meaningful behavior: non_destructive=true creates an editable filter mask rather than baking pixels, and 'exact tone tools (pixel-precise)' vs 'Krita filters' signals a fidelity distinction. However it never states what happens when layer is null (presumably active layer), whether the default path is destructive/undoable, or what the call returns — significant gaps for a mutation tool with zero annotation coverage.

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?

Purpose is front-loaded in the first clause, followed by a tightly formatted catalog that is dense but scannable and where each line names a distinct valid operation. There is minor redundancy — gamma appears both standalone and inside levels — and the bulk of the text is reference material an agent must read in full, but nothing is padding.

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 complex, four-parameter tool with 0% schema coverage and no output schema, the description supplies nearly everything an agent needs to construct a valid call, including the escape hatch to apply_filter. It falls short only on layer resolution semantics and on any hint of return/result behavior, which matter because there is no output schema to fall back on.

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 compensate, and it largely does: the operation vocabulary is enumerated exhaustively with per-operation settings keys and numeric ranges (e.g. brightness/contrast -100..100, curves points 0-255, dodge/burn exposure 0-1). The notable gap is the `layer` parameter, which is never explained despite defaulting to null.

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 opening line gives a specific verb and resource — 'Photo adjustment on a paint layer (limited to the selection if any)' — and the closing line explicitly routes non-listed Krita filters to the apply_filter sibling. What's missing is differentiation from other adjustment-flavored siblings such as auto_enhance, add_vignette, or colorize_lineart, so the agent must infer that those are separate tools.

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 a real routing rule: any filter not enumerated here should go to apply_filter, and the selection caveat tells the agent when the effect is scoped. There is no explicit 'use this when / don't use this when' for the overlapping siblings (auto_enhance, add_vignette), so guidance is clear but incomplete.

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