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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false), so the bar is lower. The description usefully adds that this creates a saved generation (a write that persists), consumes account entitlements (quota implication), and is asynchronous with get_generation as the polling tool — meaningful context beyond the 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?

Three tight sentences with the core purpose front-loaded, followed by the write/async context. No filler, though the entitlement phrase is slightly vague.

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?

With an output schema present, return values needn't be described. The async generation workflow, persistence, and the get_generation handoff are all mentioned, which is adequate for a single-parameter generation tool. The one real gap is the unexplained source union.

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% for the single 'source' parameter. The description only says the input is 'an image already in the account,' and never explains the two mutually exclusive variants (upload_id vs generation_id) that the schema enumerates. It fails to compensate for the coverage gap, adding little beyond the structural union.

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 (Restore) and resource (photo) with concrete outcomes: fixing scratches, repairing damage, restoring faded color. This distinguishes it from nearby siblings like edit_image, upscale_image, and remove_image_background, which perform different transformations.

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 implies usage — restoring old/damaged photos from an image already in the account — and notes that get_generation should be used to await the result. However, it never explicitly says when to choose this over alternatives such as edit_image or upscale_image, leaving selection to inference.

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