draw_pixels

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

Annotations only declare readOnlyHint=false and destructiveHint=false. The description adds genuinely useful behavior: a single undo step, the cel auto-growing, out-of-canvas pixels being silently dropped, and the '.'-to-transparent erase convention. It does not disclose what the tool returns or how errors surface, but the added context is well beyond the 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?

Three tightly packed sentences: purpose first, then the two input forms, then edge-case rules. No filler, no repetition of the name or schema, and the erase convention is grouped with the mapping rules it belongs to.

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 an 11-parameter mutation tool with no output schema, the description covers the tricky invocation semantics (dual input formats, coordinate origin, erasure, clipping) well. It could say more about blend/save/batch mode and return behavior, but the schema fills those and the critical pixel-writing semantics are complete.

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 coverage is 73%, so most parameters carry their own descriptions. The description still adds real meaning by explaining the pixels vs rows/legend duality, that rows start at (x,y), and the skip/mapping rules for ' ' and '.'. It leaves blend, save/batch, and backend semantics to the schema.

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 verb+resource ("Sets individual pixels on a layer/frame") and immediately characterizes the scope with "one undo step." It distinguishes itself from drawing-oriented siblings (draw_shapes, draw_image, draw_text) by describing per-pixel vs grid input, though it never names an alternative tool explicitly.

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 effectively explains the two mutually exclusive invocation modes (explicit pixels vs rows+legend) and their semantics, which is real usage guidance. However, it gives no when-to-use-this-vs-draw_image/draw_shapes guidance and no prerequisite context for choosing a backend or frame/layer target.

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