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

Annotations only say readOnlyHint=false / destructiveHint=false; the description adds the information that actually matters: the call COSTS CREDITS at the planned tier, that dry_run:true and prompt_only:true are free, and that the tool internally constructs the count assertion, keyable ground, absence of lines/labels, and a clean-cutting grid. That is real disclosure of cost, side effects, and internal guarantees that the annotations do not cover.

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 the core action and the credit warning before any detail, and the dense bullet block is justified by 18 parameters. It is on the edge of over-packed — the style-id lists ('photograph, film-still, studio-portrait...') cost words that could be deferred to sheet_options — but nothing is truly redundant.

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 an 18-param generation tool with no output schema, the description covers the workflow (quote → generate → get_sheet_atlas), the cost model, the mode variants, and the per-job parameter combinations an agent needs to call it correctly. Only low-stakes fields like project_id are left to the schema, which is acceptable.

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 already 89%, but the description adds genuine cross-parameter meaning: which kind pairs with which other params, that art_style must be a sheet_options id and does not apply to sprites, that sequences stack in order, and that @slug in subject or entity_ids attaches a saved entity. Minor gaps remain (project_id, style_ids, reference_ids get no prose), so 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?

States a specific verb and a precisely scoped artifact: ONE image holding several separately cut-out elements, and enumerates the concrete use cases (animation cycle, sprite sheet, icon set, stickers, props). It also explicitly distinguishes itself from generate_image ('never call generate_image for a sheet'), so an agent can route 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?

The 'Pick by job' section gives explicit routing rules tying each job type to a kind plus its companion params (frames + sequences + art_style, sprites + sequences, icons/stickers/props + items). It also names alternatives and prerequisites: quote with dry_run:true first, art_style ids come from sheet_options, saved entities come from list_entities, and get_sheet_atlas is the follow-up for frame rects.

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