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

The description adds meaningful behavior beyond annotations: platform restrictions (Claude Desktop), max file sizes (10MB images/100MB videos), supported formats, and the exact return value shape ({ url: 'https://...' }). These details are not in the annotations and give the agent practical expectations. The only missing piece is failure/error behavior, but annotations already cover the write/non-idempotent nature.

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 well-organized with clear headers (WHEN TO USE, SUPPORTED FORMATS, Returns) and every sentence earns its place. It is detailed without being redundant. The length is justified by the need to communicate platform-specific rules and constraints.

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?

The description covers platform limitations, formats, size limits, return value, and integration context, making it quite complete for a tool with three optional-looking parameters. The notable gap is the ambiguity around parameter requirements (one of filePath/mediaUrl likely needed) and mutual exclusivity, which is not stated. This prevents a perfect score.

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?

The input schema already documents all three parameters (folder, filePath, mediaUrl) with descriptions, so the baseline is 3. The description adds value by explaining that mediaUrl is an 'alternative to filePath' and connecting the return URL to the publish_content mediaUrl parameter. However, it fails to explicitly state that either filePath or mediaUrl is required (and arguably mutually exclusive), which would be helpful given the schema lists no required parameters.

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 opens with a clear, specific statement: 'Upload local media to cloud storage, returning a public HTTPS URL.' It further distinguishes itself from sibling tools by restricting usage to 'FOR CLAUDE DESKTOP ONLY' and naming the alternative ('For Claude.ai/web: Use create_upload_session instead'). This precisely identifies the tool's function and scope.

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 'WHEN TO USE' section provides explicit platform-specific guidance: required for Instagram, LinkedIn, Threads, X before publish_content, and explicitly not needed for TikTok (pass local path directly). It also clearly states when NOT to use the tool (Claude.ai/web) and names the alternative tool. This is exemplary usage guidance.

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