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

Annotations only declare the generic profile (non-readonly, open-world, non-idempotent, non-destructive). The description adds real workflow behavior beyond them: it returns a run to be resumed via get_concepts, it is quote-gated and cost-bearing, and it must not trigger a build without explicit user choice.

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?

Four dense but purposeful sentences, front-loaded with purpose and gating before mechanics. Information-dense rather than wasteful, though the tight run-on phrasing slightly reduces scannability.

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 usefully explains the return value (a run) and the resume path, plus the user-consent gate. Nearly complete for a gated generation tool; only the undocumented audit_id keeps it from being fully self-contained.

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 67% and the schema already carries rich prose for count (cost, reuse of existing directions) and direction. The description adds no parameter-level detail and leaves audit_id undocumented, so it does not meaningfully improve on the schema.

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+resource ('Generate visual design directions') scoped to an existing audit, and explicitly separates itself from build_page with 'Never start a build without their choice.' An agent can distinguish it from siblings like build_page and audit_page without opening any 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?

Preconditions are explicit (after the user requests designs and authorises the pack quote), it routes to check_balance for costs and get_concepts to resume, and it names an exclusion ('Never start a build'). Full when/when-not/alternative coverage.

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