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

Annotations already declare destructiveHint=true, and the leading 'MUTATES Memberful data' reinforces rather than adds. The genuinely new context is batching — one or more codes in a single call — but nothing about duplicate-code behavior, partial-success semantics, or reversibility is disclosed.

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 tight sentences with the mutation warning front-loaded, so the reader gets the risk signal first. The trailing GraphQL signature line is slightly redundant but helps an agent map to the underlying API.

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 destructive, batched mutation with no output schema, the description is silent on what comes back — created coupon objects, ids, or per-code error results — which matters when submitting multiple codes that may partially fail.

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 100%, so the schema already documents both parameters; the description only restates discountId and 'coupon code strings' and maps them onto the GraphQL argument names. That mapping is mildly useful but adds no format, constraint, or validation detail 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?

States a specific verb and resource — 'create one or more coupon codes for a discount' — and names the exact GraphQL mutation createCoupons(discountId, coupons). No sibling tool deals with coupons, so the agent can distinguish it immediately.

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 implies the call shape (must supply discountId and code strings) but never states when to use this versus the generic memberful_graphql/memberful_query siblings, nor any precondition such as the discount already existing. Usage is inferable but not guided.

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