download-bytes

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

Beyond readOnlyHint annotation, description details return format (contentType, encoding base64, contentLength, contentBytes) and warns about large file handling. No contradiction with annotations.

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?

Well-organized: first sentence states purpose and return format, then lists use cases, then alternative guidance, then parameter explanation. Every sentence adds value without unnecessary words.

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 tool with one parameter and no output schema, the description covers all needed information: what it does, how to use it (with examples), return format, and when to choose alternatives. It is fully self-contained.

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% but the description adds extensive value by explaining the target parameter with concrete, diverse examples (drive paths, mail attachments, photo, Teams hosted content). This provides contextual meaning beyond the schema's 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?

Description clearly states verb 'download', resource 'binary content from Microsoft Graph', and lists numerous specific use cases (drive file, mail attachment, profile photo, Teams content, meeting recording). Distinguishes itself from sibling tools like get-download-url and download-bytes-to-file.

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?

Explicitly advises to use get-download-url for large drive/SharePoint files and get-meeting-recording-content for meeting recordings, providing clear when-to-use-alternatives guidance. Also states it is a single tool for any binary read, setting usage scope.

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