Validate document

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

No annotations are provided, so the description carries the full burden. It discloses the result shape (per-object results plus an all_valid flag) but says nothing about whether the call mutates the document, cost on large documents, or what happens when geometry is invalid (throw vs. report).

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?

Two tight sentences: purpose and validation semantics first, usage timing second. Zero 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?

The output schema means the return values needn't be explained, and the description adds them anyway. But with no annotations and unclear mutation/safety semantics, an agent still lacks enough behavioral context to call this confidently in a destructive-adjacent workflow.

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?

One required parameter (document_id) with low schema description coverage; the description implies document scoping only through 'in a document' and never addresses the workspace default, which is documented only in the schema.

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 (validate) and resource (document geometry), and defines what 'valid' means: a Solid with positive volume. Scope ('all objects') separates it from per-object siblings like inspect_object and from recompute.

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 explicit timing guidance ('after modifying parameters or before exporting STEP') and implicitly routes the agent relative to export_step. No explicit exclusion or statement about when not to call it, and no mention of recompute as a prerequisite alternative.

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