Upload file

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that local paths only work in stdio mode, that the server reads the file itself, that large files upload asynchronously, and that with redundancyLevel > 0 only the tagId is returned immediately. It also states that references are the tool's output, not an input.

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 long but every sentence earns its place: core usage modes, routing to upload_folder, behavioral notes on sync/async uploads, and optional parameters all serve the agent's decision-making. The most critical constraints are front-loaded, and the optional parameters are logically grouped at the end.

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 no annotations and no output schema, the description is remarkably complete. It explains return behavior (reference, tagId, query_upload_progress), deferred uploads, redundancy behavior, and the alternative tool. An agent has enough information to select and invoke this tool correctly in a wide range of contexts.

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?

Although schema coverage is 100%, the description adds substantial meaning beyond the schema: it explains how to pass a filesystem path versus raw text for `data`, notes stdio-only limitation, and details the optional semantics of redundancyLevel and postageBatchId. This goes far beyond the bare schema descriptions.

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 defines the tool as uploading a SINGLE file to Swarm, with specific content modes (filesystem path or raw text). It explicitly differentiates from upload_folder by stating that this tool is for one file only, and clarifies that Swarm references are outputs, not inputs.

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 description gives explicit when-to-use and when-not-to-use guidance: if the user mentions "folder", "directory", "the contents of", or requests more than one file, the agent should use upload_folder instead. It also instructs the agent never to ask for file content when a path is given and never to pass a Swarm reference as input.

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