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

Annotations cover the safety profile (destructive, openWorld, non-idempotent), but the description adds real context beyond them: it needs explicit user authorisation and a quote, it returns an async run resumable via get_concepts, and it must not trigger a build without user choice. It does not explain irreversibility or cost mechanics beyond the authorisation gate.

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 dense sentences front-load the purpose, then prerequisites/alternatives, then the return and next-step constraint. Every sentence earns its place, though the second and third are tightly packed with multiple instructions.

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 correctly fills the gap by describing the return value ('a run to resume with get_concepts') and the follow-up display step. Combined with annotations covering the mutation profile, an agent has enough to invoke it correctly, though the cost/quote mechanics remain partly implied.

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's own descriptions already carry the meaningful parameter detail (count caps, default pack, reuse/cost behaviour, direction steer). The description adds no parameter-level semantics of its own, so the baseline of 3 is appropriate.

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 resource — 'Generate visual design directions for an existing audit' — which is clearly distinct from retrieval siblings like get_concepts and from build_page. It names sibling tools only in supportive/workflow roles rather than stating an explicit contrast, so differentiation is clear but not maximally sharp.

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?

Explicitly gates invocation on the user requesting designs and authorising the pack quote, routes cost checks to check_balance, and points to get_concepts for resuming the run. It even states a hard precondition ('Never start a build without their choice'), leaving nothing to inference.

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