download-bytes

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

Annotations indicate readOnlyHint=true (safe) and openWorldHint=true. The description adds that it returns base64 encoding, content length, and bytes, and warns about large files via alternative. No contradictions 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?

Two sentences: first states core purpose, second lists common uses and return format. Every sentence is informative with no filler. Front-loaded with key information.

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?

Given one parameter, no output schema, and rich annotations, the description covers purpose, usage boundaries, return structure, and a key exclusion. Complete for this tool's complexity.

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% with explicit parameter descriptions. The tool description does not add new semantic meaning beyond summarizing common paths; it repeats the schema info without enhancing it. Baseline of 3 is appropriate.

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 purpose: download binary content from Microsoft Graph and return as base64. It lists specific resources like drive files, mail attachments, profile photos, and Teams hosted content, distinguishing it from siblings like get-mail-message-mime or search-onedrive-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?

Explicitly says 'Single tool for any binary read' and provides a when-not-to-use example: 'For meeting recordings (often large), use get-meeting-recording-content which returns a URL...'. This guides the agent to select alternatives appropriately.

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