ap_paint_stroke

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

With no annotations provided, the description carries the full burden, and it does so richly. It discloses silent no-op conditions (no project, no selected layer, or a group layer), dependence on the selected layer and active tool/brush, the 48-point cap, and the one-frame execution constraint. This goes well beyond a generic 'paint a stroke' statement.

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?

Every sentence earns its place: the first establishes the core operation, the second explains the coordinate system, the third covers target context and failure behavior, and the final clause adds a hard limit. The density is high but the structure is logical and front-loaded with the most important information.

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?

The description covers coordinate space, no-op conditions, target layer/tool, the 48-point limit, and the single-frame execution, which is nearly complete for a drawing tool. The only minor gap is that it does not explicitly state the return value or whether the operation reports any result, though 'silently does nothing' implies no error is surfaced.

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?

The schema already describes points as normalized 0..1, but the description adds meaningful semantics beyond the schema: 0.5,0.5 maps to the viewport center, the stroke is automatically closed, and at most 48 points are allowed—a constraint not present in the schema's top-level array definition. This materially improves correct invocation.

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 specific action ('Paint a stroke in SCREEN space and close it') on a clear resource, and immediately distinguishes this tool from its sibling ap_paint_stroke_world by emphasizing screen-space normalized coordinates and camera dependence. This makes the tool's identity unmistakable.

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 clear context for when this tool applies: when you have normalized screen-space coordinates, and it notes that the painted location depends on the current camera. It does not explicitly name the world-space alternative or say 'use ap_paint_stroke_world for world coordinates,' so it falls just short of an explicit when-not/alternative statement.

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