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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive behavior. The description adds substantial behavioral context beyond that: it defines the exact verdict range, the data sources considered (90-day volumes, fees, capture-vs-reclaim), pricing ($0.05 per call, free tier), auth requirements (prepaid x-credit-token header, no wallet/API key), and that it reads a unique protocol.

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 dense but well-organized: purpose and key metrics come first, followed by verdict, uniqueness, input, and pricing/auth details. It is longer than minimal but every sentence contributes useful information. A slight structural improvement would be separating pricing/auth from the core audit behavior.

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?

Given a single required parameter, a simple address schema, rich annotations, and an output schema, the description covers all necessary context: what is audited, what verdict to expect, unique protocol access, input requirements, pricing, and access credentials. An agent has everything needed to select and invoke this tool correctly.

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?

The schema already documents the single required parameter as an 'Operator address' with 100% coverage. The description adds context by explaining that the operator is a Commerce Payments operator, not a generic address, and clarifies the required input. This is meaningful semantic enrichment beyond 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?

The description opens with a clear question ('Should you trust this Commerce Payments operator?') and then specifies exactly what the tool does: audits an operator's 90-day volumes, fees taken, capture-vs-reclaim record, and distinct payers/merchants, returning a verdict. It also explicitly differentiates itself with 'No other tool reads this new Base commerce protocol.'

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 clearly states when to use the tool: before relying on a Commerce Payments operator, because the operator drives authorization, capture, and fees. It also asserts uniqueness among all tools ('No other tool reads this new Base commerce protocol'), which strongly implies when not to use alternatives, though it does not name explicit sibling tools or provide detailed exclusion criteria.

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