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

Goes well past the annotations: it discloses the return contract (`portrait_image_id` with `portrait_status: "generating"`), that the old portrait survives in the account's images, that each repeat is a fresh charge, that the price may differ from the draft's published rate, and the exact idempotency-key replay semantics. The token-spend and go/no-go rules add real behavioral context the `destructiveHint`/`idempotentHint` flags only gesture at.

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?

Purpose is front-loaded in the first clause and the WHEN/ALTERNATIVES/CARD/AFTER/COST blocks are scannable. It is long for a four-parameter tool, and cost is stated three separate times while 'this server's instructions' is cited twice, which is some redundancy — but each block carries operational content rather than filler.

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 explains what comes back and how to follow up (don't poll the card; on a terminal, poll `portrait_image_id` with `wait_for_generation` and hand back urls). Cost, permissions-of-spend, failure recovery, and idempotency are all covered, so an agent has everything needed to call it correctly.

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 schema already documents all four params; the description adds genuine meaning on top — where `character_id` comes from, that omitting `image_model` may yield a different look and price because 'the library does not record which model drew a face,' and that `estimate_only: true` returns the exact number. Only the idempotency key's warning is a restatement of schema text.

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?

Opens with a specific verb+resource+scope: 'Redraws ONE cast member's portrait (the same character, a new image)' and explicitly bounds it as 'ONE image generation, not a new cast.' It names the sibling it is not (`describe_cast_member` for a changed character, `generate_cast_portraits` for the whole cast), so an agent can route without opening another 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?

Gives an explicit WHEN (user dislikes a face, or a portrait FAILED and blocks story creation), an explicit when-not ('never re-draft the whole cast to change one member'), and a named alternative for the adjacent case (`describe_cast_member` for a changed character). It also constrains scope: 'never redraw more members than named.'

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