Export STEP

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

With no annotations, the description carries the full burden and does disclose useful behavior: default selection is all Part objects, the default path is <workspace>/<document_id>.step, and custom paths are constrained to the controlled workspace. It does not state whether an existing file at step_path is overwritten, what permissions are needed, or whether the source document must be saved first.

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?

Three compact sentences, front-loaded with the core action and immediately followed by the selection rule and the path rule. Some content restates the schema defaults, but nothing is wasted or buried.

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?

Return values are covered by the output schema and the path/selection behavior is spelled out, so the essentials are present. For an unannotated mutation-style tool, the description should also address overwrite semantics and failure conditions, which it omits.

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 prose explains each parameter's role (object_names narrowing the export set, step_path vs the default, workspace as the containment boundary) and adds the constraint that custom paths must remain within the controlled workspace, which the schema does not state. This compensates for the reported low schema coverage and adds semantics beyond the raw field definitions.

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?

Names a specific verb (export) and resource (document objects) plus the target format (STEP), which clearly separates it from siblings like save_document or validate_document. It stops short of explicitly naming the nearest sibling as the 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?

The description gives conditional guidance for the object_names parameter (only those objects vs all Part objects) and for the output path, which implies when to use each mode. It offers no explicit guidance on when to choose this tool over save_document or other export-related workflows, leaving tool selection to inference.

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