add_shape

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

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it supplies none: it does not say which layer/selection receives the shape, whether a project must be open, whether the operation is undoable, or how shapes are named. It only offers input-format trivia (kind values, color hex), which belongs to parameter semantics, not behavior.

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 dense, front-loaded sentences with no filler; the kind enumeration and color-format note are both load-bearing. It is arguably too compressed for a 12-parameter tool, but nothing present is wasted.

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 12-parameter mutation tool with no annotations, no output schema, and 0% schema coverage, this is far short of sufficient. Critical gaps remain around defaults/optionality, the project parameter's role, stroke versus fill interaction, and what happens after the call - an agent would likely have to guess or trial-and-error.

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 for all 12 parameters. It does add real meaning for kind (rect/ellipse/line/polygon), radius (rounded corners), points (relative to x,y), and color format (#rrggbbaa for transparency) - but h, w, x, y, name, project, stroke, and stroke_width remain entirely undocumented in both places.

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 names the resource ('vector shape') and enumerates the supported kinds, but never states the action verb - it reads as a reference note on shapes rather than 'adds a shape to the project.' It also does not distinguish this tool from the sibling set_shape, so an agent cannot tell create-from-scratch apart from modify-existing without opening both schemas.

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 and no mention of alternatives, despite siblings add_text, add_image, and set_shape occupying adjacent territory. The agent is left to infer that this is the tool for drawing new vector primitives.

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