Create a direct media upload for an agent-held file. Provide the original filename and MIME type. Returns a signed_url: PUT the raw file bytes to it with the same Content-Type within 30 minutes. Once uploaded, use the returned temporary url in media_urls when creating a post. The temporary url is valid for 24 hours.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| mime_type | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: it returns a signed URL, requires a PUT with the same Content-Type, expires the URL in 30 minutes, and the temporary URL is valid for 24 hours. It also notes the file must be 'agent-held', implying the agent must have the file content. No contradictions.
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 two sentences but packs a full workflow: input requirements, the signed URL action, timing, and the post-creation integration. Every clause carries necessary information with no filler. The critical steps are front-loaded.
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 2-parameter tool with no output schema and no annotations, the description covers all needed information: what to provide, what the response is, how to act on it, and temporal constraints. An agent has everything needed to call it correctly. The only minor omission (e.g., error behavior) is negligible given the tool's simplicity.
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 schema has zero description coverage, so the description is the only source of parameter meaning. It explicitly maps 'name' to 'original filename' and 'mime_type' to 'MIME type', removing ambiguity. This adds significant semantic value beyond the bare schema definition.
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 action ('Create a direct media upload'), the resource ('for an agent-held file'), and the purpose without ambiguity. It names the tool's specific function and distinguishes it from siblings, none of which are media-upload related, so no differentiation is needed but it stands alone.
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?
Provides explicit step-by-step usage: provide filename and MIME type, PUT raw bytes to signed_url with same Content-Type within 30 minutes, then use the temporary url in media_urls when creating a post. This is an exact 'how to use' guide with timing constraints, leaving no guesswork.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.