create-onedrive-folder

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

The description explains the expected behavior: creates a folder, and through the tip, reveals that conflictBehavior can replace existing items (destructive action). This aligns with the annotation destructiveHint=true. No contradiction. It adds context beyond the schema by detailing the conflict options. However, it does not elaborate on other behavioral aspects like permissions or idempotency.

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 description is short (2 sentences + tip), but the first sentence ('Create new navigation property to children for drives') is technical and less helpful than the tip. It could be more effective by starting with the tip. Still, it avoids verbosity, earning a middle score.

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 complex tool (5 params, nested body) with no output schema, the description covers the essential aspects: folder creation, required fields, conflict handling. However, it omits details on response (e.g., returns created folder object) and auxiliary parameters (includeHeaders, excludeResponse). The schema covers most of these, but the description could be more complete.

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 high schema coverage (80%), the baseline is 3, but the description adds value by highlighting that the body must contain 'name' and 'folder' fields, and introduces the @microsoft.graph.conflictBehavior header (not in schema). This significantly aids correct invocation. The remaining properties are well-documented 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?

The description clearly states the tool creates a new folder inside a specified drive item. It distinguishes from sibling tools like upload-file-content (for files) and copy-drive-item by specifying 'folder' and mentioning folder-specific fields (name, folder property). However, it does not explicitly contrast with other create actions, which would warrant a 5.

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 provides a tip with required fields (name and folder) and conflict behavior options (rename, replace, fail), which guides usage. However, it does not specify when to use this tool versus alternatives (e.g., copy-drive-item for duplicating) or when not to use it (e.g., for files). This limited guidance justifies a 3.

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