Audit Drawing

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

The description goes well beyond the readOnlyHint annotation by stating that the drawing is mutated, repairs are already applied, results are exposed as 'fixes' and 'errors', and saving is required to persist changes. It also discloses a backend-specific behavior where counts arrive as null with detail 'unavailable' rather than zero, which is genuinely useful and not available from structured fields.

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?

The description is compact and front-loaded with the core purpose, then adds crucial behavioral and output-context details. Every sentence earns its place: mutation warning, save requirement, fixes/errors semantics, and backend null-count behavior. There is 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 parameterless tool with an output schema present, the description is complete: it explains the tool's core behavior, mutating side effects, persistence requirement, output field meaning, and a non-obvious backend quirk. An agent has enough context to invoke it correctly and interpret results.

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 has zero parameters, so the schema already fully covers parameter semantics with 100% coverage. The description correctly spends no space on parameters, and the baseline of 4 applies for a parameterless tool.

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 clearly states a specific action ('Audit the drawing') and the resource, defining what audit means: repair fixable structural problems and report results. It is clear and actionable, but it does not explicitly differentiate itself from sibling tools like validation_check, drawing_preflight, or drawing_critique.

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 implies usage: when you want structural problems fixed and reported, use this tool. It also warns that the tool mutates the drawing and that saving is required afterward. However, it provides no explicit guidance about when not to use it or which alternative tools to prefer for non-mutating validation or inspection.

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