Drawing: Critique (premium quality checks)

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

Annotations declare readOnlyHint=true and the description is consistent with that. It goes well beyond annotations by disclosing scope (every entity in model space and every paper layout, pairs compared only within a space), failure semantics (a raising check yields an `error` issue with detail.code `check_failed`, never silence), coverage limits (MAX_QA_ENTITIES, default 2,000,000, and per-layout count mismatches yielding `scan_incomplete`), and quarantine refusal.

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?

Purpose and the production-gate rule are front-loaded, and no sentence is filler. The second paragraph is dense and packs scope, error codes and limits into long clauses, which slows parsing slightly, but the information density is justified.

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 an output schema present and a fully documented single parameter, the description only needed to cover behavior, failure modes and the gate, all of which it does. An agent can call this correctly and interpret both issues and refusals without further inference.

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 100% and the schema already enumerates every focus name with per-family silence behavior, so a baseline 3 would apply. The description adds genuine meaning beyond the schema by explaining that the four entity checks scan all spaces and compare only within one space, which informs how focus values behave.

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 action (run quality checks over the whole drawing, returning an issue list, empty when clean) and clarifies the gate role before drawing_finalize. It never distinguishes itself from the numerous related siblings (validation_check, drawing_preflight, drawing_verify_requirements, drawing_audit, drawing_topology_check), so an agent cannot tell 'premium-quality checks' apart from those without trial.

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?

It gives explicit use context: a standard production gate that must return [] before `drawing_finalize`. No when-not guidance or routing to the similar validation/preflight/topology siblings, which is the main remaining ambiguity.

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