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

Annotations already declare destructive=true and idempotent=false; the description adds real value by disclosing the downstream effect that future periods are no longer expected and framing the reason field as the place to capture timing. It stops short of saying whether cancellation is reversible, which is a notable gap for a destructive, non-idempotent operation.

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?

Front-loaded with the action and the key semantic distinction, then effects. The trailing 'Effects: subscription cancelled.' largely restates the opening sentence and is close to wasted text.

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 two-param mutation with rich annotations and no output schema, the description covers purpose, the fact-vs-inference rule, and downstream effect. The main missing piece is reversibility/undo path, which matters given destructive=true.

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 params. The description says to record when in the reason, matching the schema's own 'Why, and when if you know' — marginal added value over structured data. Baseline 3 applies.

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 ('Record that a subscription was cancelled') and immediately contrasts with the automatic 'lapsed' state, which differentiates it from inference-driven sibling behavior like purch_subscriptions or purch_declare_subscription.

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?

Gives explicit when/when-not guidance: only record when the person states cancellation, not when charging merely stops. It does not name a specific sibling tool as the alternative, but the semantic boundary (fact vs. inferred lapse) is clear enough to route an agent.

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