Microsoft 365 MCP Server

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

With readOnlyHint=true in annotations, the description adds the important constraint that this only works 'if the item represents a file' (not folders). However, it omits behavioral details about streaming large files, pagination handling via fetchAllPages, or format conversion capabilities implied by the format parameter.

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?

While brief (one sentence), this is under-specification masquerading as conciseness. The sentence describes output behavior rather than tool purpose, failing to front-load actionable information for the agent.

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?

Without an output schema, the description attempts to describe the return value but misses critical context for a download operation: error conditions (file not found, permission denied), binary vs text handling, or the interaction between format conversion and the content stream.

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 coverage is 100%, establishing a baseline of 3. The description adds no semantic context for parameters (e.g., explaining that driveId identifies the OneDrive drive rather than just restating 'Path parameter'). It leaves the technical schema descriptions as the sole source of truth.

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 uses a noun phrase ('The content stream') rather than stating the action (download/retrieve), and describes the return value conditionally rather than the tool's purpose. It fails to distinguish this from sibling list/get operations like get-drive-root-item or list-folder-files.

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 provided on when to use this versus listing files or getting metadata. No mention of prerequisites (e.g., needing file IDs from list-folder-files) or when to use flags like excludeResponse versus includeHeaders.

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