Drawing: Refine

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

The annotations already flag destructiveHint=true, and the description adds useful context by noting the loop is bounded and transaction-safe. However, it does not clarify what 'transaction-safe' means in practice—whether the tool starts its own transaction, requires transaction_begin/commit, or rolls back on failure—or what side effects a repair has on the drawing.

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?

One short, front-loaded sentence conveys the core behavior without filler. Every word adds meaning: 'bounded' hints at max rounds, 'transaction-safe' signals safety, and 'critique/repair/re-critique' describes the loop.

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?

Despite having an output schema and parameter descriptions, the tool definition is incomplete for a complex mutation tool. It does not explain how dry_run interacts with the loop, what triggers completion (min_score, max_rounds), or how transactions are scoped, leaving an agent uncertain about correct invocation and rollback behavior.

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 description adds no parameter-level meaning, and schema coverage is only 60%, leaving min_score and max_rounds undocumented in the schema. Focus, dry_run, and allowed_repairs have schema descriptions, but min_score's threshold meaning and max_rounds' relationship to the loop are not clarified; the vague 'bounded' in the description does not compensate.

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 clear verb and resource: it runs a bounded critique/repair/re-critique loop rather than a one-shot critique, which distinguishes it from drawing_critique. It could be more explicit by naming sibling tools such as drawing_critique or drawing_plan, so it is clear but not fully differentiated.

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 is given about when to use this tool versus drawing_critique, drawing_preflight, or drawing_plan, and no exclusions or alternatives are named. The reader must infer that the loop is meant for iterative refinement; the description does not state this directly.

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