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

The description labels the tool "[read]" and describes purely passive waiting with no side effects, which directly contradicts the supplied annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=false). Per the rubric this is an annotation contradiction. Everything else it discloses (termination states DONE/FAILED/CANCELED, cancel_character_image producing CANCELED, timeout semantics, extra `finished`/`waited_seconds` fields) is genuinely useful but cannot offset the safety-profile conflict.

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?

Front-loaded with purpose and the no-polling rationale, then timeout behavior and return shape; no filler sentences. It is dense — one long sentence enumerating five creator tools and a second packing three terminal states plus cancel_character_image — but every clause carries information.

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 no output schema, the description still specifies the return: fields of get_character_image plus `finished` and `waited_seconds`, and what `track` values mean in each branch. Combined with the timeout and retry guidance, an agent has everything needed to call it and interpret the result.

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 0%, so the description must carry all parameter meaning and largely does: `image_id`/`image_uuid` are alternative identifiers for the image being waited on, and `timeout_seconds` is default 60 with a hard cap of 120 plus the documented consequence of exceeding it. The only gap is that it never says whether image_id and image_uuid are mutually exclusive or that one is effectively required.

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?

Names a specific verb+resource ("Wait for a picture ... to finish") and enumerates exactly which creation tools produce the artifact being waited on (create_character_image, create_character_thumbnail, create_replace_image, create_promo_image, create_infographic_image). It also disambiguates from the polling sibling get_character_image, so an agent can select it without opening a schema.

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?

Explicit when-to-use: instead of polling with get_character_image, because the call returns as soon as track is DONE/FAILED/CANCELED. It also gives the follow-up rule — if `finished` is false after the timeout, call it again to keep waiting. Alternatives and exclusions are both stated.

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