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

Annotations only supply destructiveHint=true; the description carries the rest and does so well, marking it as a WRITE, stressing that it mutates a real customer's billing, and naming the endpoint (PATCH /subscriptions/{id}). It does not disclose side effects an agent would want, such as proration on plan change or reversibility of a cancel, so it is strong but not exhaustive.

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?

Two compact sentences at most, front-loaded with the "WRITE:" warning before the capability list, then the endpoint. No filler and the most decision-relevant information (write, live, billing impact) comes first.

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 one-resource mutation with no output schema, the description supplies the operation type, target, mutation modes, blast radius, and endpoint — enough to call it responsibly. What is missing is behavioral detail on the mutation itself: whether plan switches prorate, whether a cancel here differs from the dedicated cancel tool, and whether supplying multiple fields in one call is supported.

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 100%, so every parameter already carries its own documentation and the baseline is 3. The description restates the parameter purposes inline (variant_id for plan/tier, pause/unpause, billing anchor) without adding format, constraints, or interaction rules 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?

"WRITE: Modify a LIVE subscription" gives a specific verb (modify), resource (live subscription) and enumerates the exact mutation modes (plan/tier via variant_id, cancel, pause/unpause, billing anchor), so the agent knows precisely what this call changes. It stops short of differentiating from the sibling `lemonsqueezy_cancel_customer_subscription`, even though "cancel" is listed among the modes here, leaving a small overlap unresolved.

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?

"This affects a real customer's billing" implies caution and live-subscription scope, and "LIVE" hints at a precondition, but there is no explicit when-to-use guidance, no statement of when NOT to use it (e.g. versus the dedicated cancel tool), and no instruction on which of the five optional fields must be supplied together. Usage is inferable but not stated.

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