Drawing: Preflight

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

With readOnlyHint already declaring the safety profile, the description still adds substantial behavioral context: nothing is refused (problems surface as questions/conflicts), `ready` remains False until the question set is empty, conflicts are kept rather than collapsed, and MISSING_UNITS is raised only once units are known. None of this is derivable from the annotations or schema.

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 purpose statement is front-loaded and the dense detail that follows is reference-grade rather than filler. It is long and backtick-heavy, but nearly every clause carries operational meaning; only the legacy-dimensions aside could be trimmed without loss.

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?

An output schema exists, so return-shape explanation is rightly omitted, and the description covers the non-obvious semantics (conflict codes, normalization, the ready gate). It stops short of telling the agent what to do when `ready` is False — which sibling resolves the questions — but that is the only meaningful gap.

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 already 75%, and the description adds real meaning on top for the hardest parameter, `requirements` — typed `items` shape, the legacy `dimensions` escape hatch being kept read-only and never measured, and where the canonical form lands (`normalized_spec`, `spec_hash`, `requirement_set`). The remaining top-level scalars (scale, sheet_size, view_count, layer_set_id) are covered by schema text and left alone, which is appropriate.

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 opening line names a specific verb+resource pair (validate/normalize requirements) and situates it in a workflow phase ("before committing a drawing plan"). It does not name a sibling like drawing_verify_requirements or drawing_plan explicitly, so an agent must infer the boundary from the phase hint rather than from a stated alternative.

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?

Timing is implied by "before committing a drawing plan", which tells the agent roughly where this sits. However, there is no explicit when-not guidance and no named alternative for related tasks (verify requirements, critique, plan), leaving sibling selection partly to inference across a very crowded namespace.

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