Microsoft 365 MCP Server

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

The annotations already provide critical behavioral information: readOnlyHint=false (mutation), destructiveHint=true (destructive operation), and openWorldHint=true (can affect external state). The description adds no additional behavioral context beyond what annotations already declare. However, it doesn't contradict the annotations, so it gets a baseline score for not misleading the agent about the tool's behavior.

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 a single sentence that's technically concise but poorly structured for clarity. While brief, it uses confusing terminology ('navigation property items') that doesn't effectively communicate the tool's purpose. The description is front-loaded but fails to convey essential information efficiently, making it less helpful than it could be despite its brevity.

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 destructive operation tool with no output schema, the description is inadequate. It doesn't explain what happens when a file is deleted (permanently? moved to trash?), what permissions are required, or what the response contains. The annotations cover safety aspects, but the description should provide more operational context for a tool that permanently removes data. Given the complexity and risk of file deletion, more guidance is needed.

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 description coverage is 100%, so all parameters are documented in the schema. The description adds no parameter information beyond what's already in the schema. It doesn't explain what 'driveId' and 'driveItemId' represent, how to obtain them, or provide context about the optional headers parameters. With complete schema coverage, the baseline is 3 even without additional parameter semantics in the description.

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 'Delete navigation property items for drives' is vague and confusing. It doesn't clearly state that this tool deletes a OneDrive file, which is implied by the tool name. The phrase 'navigation property items' is technical jargon that doesn't clearly communicate the tool's function to an AI agent. While it mentions 'delete' and 'drives', it lacks the specific verb+resource clarity needed for proper tool selection.

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 no guidance on when to use this tool versus alternatives. There are multiple delete-related sibling tools (delete-calendar-event, delete-mail-attachment, etc.), but the description doesn't differentiate this OneDrive file deletion tool from those or explain when it's appropriate. No context about prerequisites, alternatives, or exclusion criteria is provided.

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