plan_illustrationsList the illustrations each screen needs (none, one or several); the reply gives per_screen and the routes for the user to approve.
| Name | Required | Description | Default |
|---|---|---|---|
| illustrations | No | The illustrations the design needs: {name, shows, screens: [the artboards it goes on]}, one subject each. A screen may have none, one or several; ui: a drawing is never shared. An empty list means the design has none. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true, but the description does not disclose what may be destroyed or modified, nor does it explain the approval workflow in enough detail. 'List' and 'routes for the user to approve' undersell the destructive annotation without explicitly contradicting it.
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 description is a single front-loaded sentence with no filler. It is concise, though terms like 'per_screen' and 'routes' are unexplained and slightly cryptic.
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 and a destructive annotation, the description should explain return values and mutation/approval behavior more fully. It mentions per_screen and routes but does not clarify what is written, what approval changes, or how this relates to sibling illustration tools.
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%, and the single illustrations parameter is already richly documented in the schema, including the {name, shows, screens} structure and the empty-list case. The description adds no parameter meaning beyond what the schema provides, which is acceptable given full coverage.
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 states a verb and resource: it lists the illustrations each screen needs and returns per_screen routes for approval. However, it is vague about what 'plan' means versus sibling tools like generate_illustration, illustration_jobs, and create_icon, so an agent cannot confidently distinguish it from those alternatives.
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 description gives no explicit guidance on when to use this tool versus alternatives such as generate_illustration or illustration_jobs. It implies a planning/approval workflow but does not state prerequisites, exclusions, or selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.