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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false) by disclosing the moderation behavior: refused images are never served, the error explains why, and the agent should tell the user and request a new image. This is exactly the kind of failure-mode context an agent needs and cannot get from structured fields.

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 primary purpose and return value are front-loaded in the first sentence, and the moderation caveat follows as actionable guidance. Slightly sprawling due to the mid-sentence line break, but every sentence earns its place.

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?

An output schema exists, so return values need not be re-explained, and the description covers the critical edge case (moderation refusal and recovery). An agent has everything needed to call this correctly and handle failure.

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% and the single asset_id parameter is already documented as coming from start_image_upload. The description's reference format (_img/<id>.jpg) describes the return value rather than adding parameter semantics, so the baseline 3 applies.

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?

States a specific verb+resource ('Finish an upload') and its output ('returns the reference to use in the page'). It is clearly distinguishable from the sibling start_image_upload since this is the completion step of the same flow.

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?

'Finish an upload' plus the schema note tying asset_id to start_image_upload makes the sequencing clear. It doesn't explicitly name start_image_upload as the prerequisite step or state when not to call it, but the context is unambiguous for an upload-completion tool.

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