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

Beyond the annotations (which only say it's a non-destructive, non-open-world write), the description discloses that the call is free with the prep fee deferred to creation and already reflected in quote_avatar, that the upload link is single-use with a 5-minute TTL, and that failures return a reason plus a fix path. The consent/real-person rule adds a policy side effect an agent could not infer from the schema. No contradiction with the supplied hints.

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 content is worth keeping but the packaging is weak — a run-on opening, a price aside wedged mid-sentence, and the recipe list crammed into the same paragraph as the control flow. Front-loading exists but is buried under the 'FREE:' prefix, and the multi-step call sequence would read far better as ordered bullets.

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 6-parameter, no-output-schema tool it covers the two call paths, the error/retry loop, upload-link lifetime, and the image recipe (framing, centering, background color, resolution, style, no watermark), which is a lot of what an agent needs to succeed. The gap is the success return: it says the check 'runs' but not what a passing result looks like or whether a reference is persisted.

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 would be 3, but the description adds real meaning: ownImageRef is the token to use on a second call after uploading, imageUrl must be public https, and consent/real_person are only actionable when the user asserts ownership or permission. It also explains that language drives replies and prices. It does not clarify how framing interacts with the 'knees-up' recipe guidance, leaving a small gap.

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 concrete verb chain — hand over a reference image, register it, and run the check — and distinguishes the two input paths (imageUrl vs ownImageRef/upload). It also ties the fee behavior to the sibling quote_avatar, which helps place it in the pipeline. It falls short of 5 because the opening phrase ('hands Ania a reference image... then runs the check') is idiosyncratic and the tool's core outcome is never stated in a single clean clause.

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?

Guidance is explicit on the branch conditions: with a public https imageUrl, register and check; without one, call to get an upload link and then call again with ownImageRef. The consent/real_person precondition is also spelled out conditionally. It stops short of 5 because it never states when to prefer this over the adjacent image tools (adjust_image, approve_image) or what stage of the avatar flow it belongs to.

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