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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: the local-only constraint, the deduplication behavior (exists field), and the fact that credits are deducted. It doesn't explicitly state that the operation is a write/upload, but the description's 'Upload' verb and the credits_deducted return field make that clear. The description adds context beyond annotations without contradicting them.

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 well-structured and front-loaded: the core purpose is in the first sentence, followed by the critical usage constraint, then a usage example, then parameter details. Every sentence earns its place, and the Args/Returns section is a clean, scannable format. 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?

The description is complete for an upload tool. It covers the purpose, the local-only constraint, the alternative for remote connections, how to use the result, parameter semantics, and the return value structure. The output schema exists, so return values are documented. The sibling tools are all different operations (generate, checkout, account management), so no confusion is possible. Nothing an agent needs to call this correctly is missing.

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 the schema already documents both parameters (file_path and filename). The description adds a small amount of value by explaining that filename is inferred from file_path if omitted, which is also in the schema. It doesn't add format details or examples beyond what the schema provides, so a baseline 3 is appropriate.

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 states a specific verb ('Upload'), a resource ('a local image'), and the outcome ('get a CDN URL for img2img or --sref'). It clearly distinguishes this tool from siblings like generate or get_generation by focusing on the upload step. The title and description align, and the purpose is immediately understandable.

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: only on local (stdio) connections, and provides the alternative for hosted/remote connections (place an existing image URL directly in the prompt). It also gives a concrete usage example showing how to use the returned URL in a generate prompt. This is clear, actionable guidance that prevents misuse.

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