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

The description claims 'retries do not create another upload' and tells the caller to retry with the same arguments to read stable operation state, which is an idempotency guarantee. However, the annotations declare idempotentHint=false, directly contradicting that claim. This is an annotation contradiction that undermines the tool's behavioral contract.

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?

Five dense sentences, each earning its place: purpose, retry behavior, processing mode default, asset-set rules, and sibling routing. The most important information is front-loaded, and there is no filler or repetition.

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 12-parameter tool with no output schema, the description covers the asynchronous queue behavior, how to poll via retry, required asset shape, and input exclusions. It does not describe the operation status/result shape or failure semantics explicitly, and the idempotency contradiction weakens overall reliability.

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 coverage is 100%, so the baseline is 3. The description adds useful cross-parameter semantics: processing_mode defaults to background removal, 'none' stores originals as-is, the asset set must contain exactly one full front with unique full views, and detail views can repeat. These constraints help an agent construct the assets array correctly, going slightly beyond the 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 names a specific action—queue a recoverable batch upload from public HTTP(S) image URLs—and clearly distinguishes it from the chat-file and local-file sibling tools. An agent can immediately tell what resource this operates on and how it differs from upload_garment_from_chat_file and prepare_local_garment_upload.

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 explicitly states when to use this tool versus alternatives: 'For ChatGPT attachments, use upload_garment_from_chat_file instead. For local filesystem files, use prepare_local_garment_upload instead.' It also lists explicit exclusions ('No base64, chat file objects, or local paths'), leaving no ambiguity about appropriate inputs.

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