Drawing: Refine

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

Annotations already indicate destructiveHint. Description adds that it is bounded (max_rounds) and transaction-safe, providing some behavioral context. However, it does not elaborate on side effects like modification to the drawing or that it may require transactions to be started/committed.

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?

Single sentence is concise and front-loaded with key terms (bounded, transaction-safe). It is appropriate in length for a tool description, though could include more detail without losing conciseness.

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?

With 5 optional parameters, an output schema, and many sibling tools, the description is too brief to be complete. It omits context about working on the current drawing, interactions with transactions, and expected outcomes.

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 tool description does not add meaning to the parameters beyond the input schema. Only 60% of parameters have descriptions in the schema, and the description gives no extra context on focus, dry_run, etc.

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 process: bounded, transaction-safe critique/repair/re-critique loop. It distinguishes from plain critique by indicating iteration, but could more clearly differentiate from sibling tools like drawing_critique or drawing_plan.

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?

No guidance on when to use this tool over alternatives. The description does not mention prerequisites, when to choose this vs manual repair steps, or that it is for automated refinement.

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