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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, and the description adds genuinely useful behaviour: it is a paid operation with resolution-dependent cost starting at 50 credits, it returns a project id that must be polled via wait_for_image_project, and availability of a listed setting is account-dependent. However, part of that guidance is generic boilerplate ('model, resolution, duration or count') that does not map to this tool's parameters, and it never states what happens on failure or whether a rejected request is charged.

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 core capability and the cost/async-return sentence are front-loaded and useful, but the opening paragraph is a policy block placed ahead of the purpose statement, and the closing sentences ('Preserve explicit requirements and all supplied inputs…', 'Account balance alone does not prove a request is affordable') are generic scaffolding that dilutes the tool-specific content.

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 three-parameter, nested-object generation tool with an output schema and full schema coverage, the description covers the important gaps: authorization constraints, credit cost, account-dependent availability, and the wait_for_image_project follow-up. Return-value detail is rightly omitted because an output schema exists, so only the missing sibling differentiation and failure semantics keep this from a 5.

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 baseline is 3, but the description adds meaning beyond the schema by tying the resolution enum to the billing model ('cost depends on resolution, from 50 credits at 640px') and by warning that a listed resolution may not be available on the account. The nested asset paths (person_file_path, scene_file_path) are left entirely to the schema's upload-guide links, so it is not a full 5.

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 gives a concrete verb and resource: 'Places a person from one supplied photo into a supplied scene image', and the cost/return sentence confirms it is an asynchronous image-generation job. It is clear on its own, but it never distinguishes itself from near-neighbours in the sibling list such as swap_face_in_photo, swap_head_in_photo or change_clothes_in_photo, so an agent choosing among them gets no routing signal.

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?

It gives real usage conditions: only with the user's own likeness or authorized content, never for impersonation, deception, sexual content or minors, and it instructs reading get_account_info and checking current parameter constraints before setting resolution. What is missing is an explicit statement of which alternative tool to use for the adjacent tasks (face swap, head swap, character replacement in video).

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