fusion_export

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

Since no annotations are provided, the description must carry the full behavioral burden. It does disclose one meaningful trait: 'Existing destinations are rejected,' indicating a fail-if-exists behavior rather than overwrite. However, it doesn't state what happens on success (return value, output), whether the parent directory must exist, error handling, or permission requirements. Useful but incomplete.

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 tightly packed sentences with zero filler. Every clause earns its place: the format list, the path requirement, and the rejection behavior. The key scoping constraints are front-loaded before any detail an agent would only skim.

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?

For a 3-parameter export tool with no annotations and no output schema, the description covers format selection and path requirements reasonably well. The main gap is the unexplained 'entity' parameter, which is likely essential for format-specific exports like DXF (choosing which sketch) or BOM (which component). That gap leaves an agent guessing on a required detail of the operation.

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?

With 0% schema description coverage, the description must compensate for the schema. It does add meaning beyond the raw enum by expanding the format codes into readable names (e.g., 'f3d' → 'F3D archive') and by specifying that path must be 'a new absolute path.' However, the 'entity' parameter is not mentioned at all — an agent has no idea what entity refers to (likely the specific sketch for DXF or component to export) — and the description doesn't clarify which formats require an entity.

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 verb ('Export'), the exact resources (STEP, STL, F3D archive, sketch DXF, BOM JSON), and a critical constraint (new absolute path, existing destinations rejected). This clearly separates it from siblings like fusion_screenshot, fusion_bom, and the CAM tools — an agent can immediately identify this as the file-export operation.

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?

No guidance on when to use this tool versus alternatives. For example, an agent wanting BOM data has both fusion_bom and fusion_export with bom_json format available, but the description doesn't explain which to choose or in what scenario. The only usage hint is the rejection of existing destinations, which is a constraint rather than a when-to-use directive.

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