Draw

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

The description discloses behavior beyond the annotations: operations are applied as a single undoable action, paletteLock snaps colors perceptually before writes, ops run in array order, and the tool cannot silently widen the palette. This gives an agent a clear model of side effects and sequencing, especially useful since the annotations are all false and uninformative.

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 focused sentences: first states what it does, second gives the critical batching/undo guidance, third covers ordering and palette safety. Every sentence earns its place with no filler.

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 tool with 11 op types and 8 parameters, the description covers the essential behavioral model: batching, undo, paletteLock, and execution order. The rich input schema and output schema cover parameter details and return values, so the remaining gaps (e.g., selection-only clipping, createCel behavior) are adequately handled by schema descriptions rather than requiring narrative.

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 100%, so the baseline applies. The description reinforces paletteLock semantics and op ordering, but these are also present in the schema ('Applied in order, in one transaction', 'Snap every colour to the nearest palette entry'). It adds little genuinely new meaning beyond the structured 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 and resource: 'Apply a batch of drawing operations to one cel'. The list of supported ops (pixels, line, rect, fill, etc.) makes the tool's scope unmistakable and clearly distinguishes it from sibling tools like frame, layer, or transform.

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?

Provides clear usage direction: batch aggressively, treat one whole sprite as a normal call, and rely on the single-undo behavior. It also explains when paletteLock should be kept at its default. It does not explicitly name alternative tools for non-drawing actions, but the operational guidance for how to use the tool is strong.

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