Design Generate

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

Annotations declare readOnlyHint=false but destructiveHint=false and idempotent=true, which alone is ambiguous. The description resolves this by stating "Never uploads; it returns the claude-design MCP calls to make" – an important disclosure that the tool plans rather than performs side effects, plus the return shape. It does not cover permissions or failure behavior, so 4 rather than 5.

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?

Three short, front-loaded blocks: what it produces, when to use it, and what it returns. No filler; every sentence carries routing or behavioral 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?

Despite having an output schema, the description still summarizes the return contract, and it supplies the pipeline precondition, the non-execution guarantee, and the next sibling to call. For a single-parameter planning tool in a long tool list, nothing an agent needs to invoke it correctly is missing.

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?

Only one parameter (app_dir) and schema description coverage is 100%, including an example path, so the schema already carries the semantics. The description adds nothing about app_dir beyond what the schema states, which is the baseline 3 case.

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 (prepare) plus the concrete resource (the app's Claude Design project) and enumerates the artifacts produced: scaffolds, mascot boards, canvas, store layout, upload plan. An agent can distinguish it from siblings like design_screens_skeleton or design_research_check 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?

Gives an explicit precondition ("Use when: after design_research_check passes") and a follow-up routing ("Then record with design_record_upload"), which is strong positioning within the design_* pipeline. It stops short of an explicit when-not-to-use statement, so it is clear context rather than a full routing rule.

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