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

Annotations are minimal (readOnlyHint=false, idempotentHint=true, destructiveHint=false). The description significantly adds context: it may CREATE a referral code on first use, requires explicit approval, lists are bounded by backend limits, and it returns an approval URL first with no change until separate human approval. This goes well beyond the annotations and discloses side effects clearly. No contradiction with annotations.

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 a dense paragraph, but every sentence adds essential information: purpose, side effect, approval flow, bounded lists, exclusions, and idempotency guidance. It is front-loaded with the main purpose and then lists caveats. Slightly long but efficient.

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?

The tool has an output schema, so return values are covered elsewhere. The description covers side effects, approval requirements, bounded lists, and what it doesn't do. The only notable gap is parameter semantics for 'details', which is missing. Given the complexity and the existence of an output schema, the description is otherwise fairly complete.

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 has two parameters (requestId and details) with 0% description coverage. The description mentions reusing 'the identical requestId and details' but does not explain what 'details' should contain or the format of requestId beyond what the schema provides. With zero schema coverage, the description must compensate, but it offers no parameter-level guidance.

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 states a specific verb and resource: 'Open this merchant referral program' and enumerates the data returned (link/code, counts, referred merchants, balances, earnings, payout history). It is clear and distinct from the 40+ sibling tools, none of which target referral programs.

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 explains when to use this tool (to open the referral program) and explicitly lists what it does NOT do (approve rewards, request a transfer, record a payout). It also instructs reusing the same requestId and details to retrieve results, which serves as a usage hint. It doesn't name alternative tools, but the exclusions provide adequate guidance.

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