upload_document

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

Annotations are minimal (readOnlyHint false, destructiveHint false). The description adds value by detailing the process: reads from disk, requests pre-signed S3 URL, streams bytes, returns metadata. This goes beyond the structured fields. 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?

The description is two sentences with the main purpose front-loaded. It is concise but could be more structured (e.g., separate bullet for supported formats). No wasted 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?

Given the tool's simplicity (3 params, no output schema, minimal annotations), the description covers usage, process, supported formats, and size limit. It is complete enough for an agent to invoke correctly, though it could mention error scenarios or exact metadata returned.

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 description coverage is 100%, so baseline is 3. The description adds minimal extra meaning: for contentType it lists recognized extensions, but overall the schema already documents the parameters well. No significant improvement beyond schema.

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 'Upload a local file to SignaTrust and return a document ID suitable for passing to create_envelope', specifying the verb (upload), resource (local file to SignaTrust), and the intended downstream usage. It distinguishes from sibling tools like analyze_document and create_envelope.

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 provides context on when to use (to get a document for an envelope), supported formats (PDF, DOCX, images), and max size enforcement. However, it lacks explicit guidance on when not to use or alternatives if the file is not local.

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