drawing_gate

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

With no annotations at all, the description carries the entire behavioral burden and does so: it enumerates the violation taxonomy (under/redundant/conflict/extra/no_datum/not_ballooned) with meanings, defines ok=True semantics, explains the DOF-accounting and process-aware ('prismatic' vs 'turned') rules, and discloses the returned payload keys plus the ballooned summary being reported even when not required. This is unusually rich disclosure for a validator.

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?

Front-loaded with the purpose and the checks it performs, then proceeds to return payload and violation codes. Dense and long, but nearly every sentence supplies non-obvious semantics; the violation-code enumeration is worth its length, though the prose could be trimmed slightly.

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?

There is no output schema, so the description must describe returns — and it lists the full response shape, explains section_recommended's sub-fields, and defines what an empty violations list means. Given the tool's complexity, an agent has everything needed to call and interpret it.

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 0%, so the description must supply all parameter meaning, and it does: process='auto' infers from geometry with 'prismatic'/'turned' behaviors described; datums_declared forces the datum check on without annotated datums; require_ballooned demands a balloon per characteristic and its failure mode. Only 'page' is left implicit, which is self-evident from context.

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 — validates the *drawing* itself by checking whether the placed dimension set fully and non-redundantly reconstructs the part — and explicitly distinguishes itself from the sibling geometry gate ('the way the geometry-realizes-declaration gate validates an assembly'). An agent can tell this apart from drawing_legibility, gdt_check, or verify_feature without opening any schema.

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?

Gives clear triggering context: IT is the gate to run when deciding whether a drawing is manufacturing-complete, and it names the conditions that activate extra checks (datum-origin discipline auto-on, datums_declared=True to force it, require_ballooned=True for release flows). It cross-references relevant siblings (add_section_view, balloon_drawing, annotate_face) but never states when to prefer it over drawing_legibility or gdt_check, so it falls short of full when/when-not routing.

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