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

Annotations already declare readOnly=false, idempotent=true, destructive=false and openWorld=false, so the bar is lower; the description still adds real context: files are 'bounded', the target application must be email-verified, and the version must match exactly, implying conflict behavior. It stops short of stating what a version mismatch or idempotent replay actually returns.

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?

A single front-loaded sentence with no filler, stating resource before constraints. It is densely packed with qualifiers, which slightly hurts scannability but nothing is wasted.

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?

Output schema and annotations relieve it of covering returns and safety, and the description flags the version and idempotency risks. However, for an 8-required-parameter mutation with 0% schema descriptions, the missing explanation of contextKey and sessionToken leaves an agent guessing how to target the application at all.

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 0% across 8 required parameters, so the description must carry the load, but it only gestures at expectedVersion, idempotencyKey, mimeType and size. The two most opaque parameters, contextKey and sessionToken, plus contentBase64 encoding and fileName rules, get no explanation beyond their names.

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?

Specific verb+resource ('Upload ... document to ... application') with concrete constraints: one file, allowed formats, exact version, idempotency key. It does not differentiate itself from the closely named siblings applications.create_document_upload and applications.complete_document_upload, leaving the agent to infer the place in the upload lifecycle.

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?

Preconditions are implied ('email-verified application', 'exact version'), which hints at when this call is valid, but no alternative is named and no explicit when-not guidance is given, even though create_document_upload and complete_document_upload are obvious candidates to route against.

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