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

Beyond the annotations, the description reveals that this records agent-reported rather than human-click evidence, that it does not constitute payment consent, that the artwork/configuration is immutable, and that identical repeated approvals are idempotent. It even states the return fields approvalId, evidence, and expiry. This adds substantial behavioral context.

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 front-loaded with the most important precondition and every subsequent sentence adds distinct value: evidence semantics, idempotency, change handling, and reuse rules. Despite its length, there is no fluff or redundancy.

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 a write operation with no output schema, the description covers prerequisites, side-effect boundaries, idempotency, change policy, reuse conditions, and return fields. An agent has enough context to invoke it correctly and avoid treating it as payment consent or independent verification.

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 only 17%, so the description must compensate. It does explain the meaning and conditions for frontReviewed, backReviewed, and artworkApproved, and guestToken is fully documented in the schema. However, designToken and quoteToken receive no semantic explanation in either the schema or the description, leaving their roles partially implicit.

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 clearly states the tool records agent-reported artwork approval and explicitly distinguishes it from independent human-click evidence and payment consent. The verb 'Records' plus the resource 'customer proof approval' make the purpose unambiguous and distinguishable from sibling tools like refresh_design_proof.

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?

It gives an explicit precondition: only call after showing both previews, warnings, print options, and receiving explicit customer approval in the AI conversation. It also states when fresh approval is required and when a previous artwork approval can be reused, providing clear when-to-use and when-not-to-use guidance.

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