add_fill

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

With no annotations, the description carries the full behavioral burden, and it does disclose real geometry semantics (angle 90 = left->right, 180 = top->bottom; cx/cy as fractions; 0-based stacking via index). It is silent on whether this creates a new layer, how it interacts with the existing canvas content, and any permission or project requirements, which is a notable gap for a mutation tool.

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 tight sentences, front-loaded with the scope ('Full-canvas fill') and packed with notation instead of prose. It wastes no words, though the parenthetical angle/center details could be slightly clearer in ordering.

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 9-parameter creator tool with no annotations and no output schema, the description is thin: it never says a new layer is created, what the return is, how name/project behave, or how index interacts with existing layers beyond the background hint. An agent could call it but would be guessing on several parameters.

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% across 9 parameters, so the description must compensate and only partially does: it explains angle, cx, cy, index, and implies kind via the fill-type list. color, color2, name, and project receive no explanation at all, and 'kind' is never explicitly named as the selector.

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 concrete verb and resource ('Full-canvas fill') and enumerates the fill variants it supports (solid, linear gradient, radial), so an agent knows what the tool produces. It does not, however, differentiate itself from the sibling set_fill, so the boundary between creating a fill versus modifying one is left implicit.

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 weak usage hint ('index=0 puts it at the bottom (a background)'), which tells the agent when to use a low index, but there is no guidance on when to choose add_fill over set_fill or add_shape with a fill. No prerequisites or exclusions are given.

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