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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the bar is lower; the description still adds real value by spelling out the downstream effects (billing and deliveries stop) and that only the merchant can re-activate. It does not say what happens if the tool is invoked on an already-cancelled subscription, leaving the non-idempotent behavior unexplained.

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 operation and its effects, then scope disambiguation, then the confirmation instruction. Every clause carries information an agent would otherwise have to guess.

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 two-parameter mutation with no output schema, the description covers effects, reversibility, and the confirmation requirement. What the call returns and how errors (invalid or already-cancelled id) surface is unstated.

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%, and the schema itself points subscription_id at recurpay_list_subscriptions and gives an example reason format. The description adds no parameter-level detail beyond that, so 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?

Specific verb+resource ('cancel one subscriber's subscription in Recurpay') plus the state transition ('status becomes cancelled; billing and deliveries stop'). It also pre-empts a plausible misread by stating this is the merchant's action on a customer subscription, not cancellation of the MCP server's own plan, which separates it from the read/list siblings.

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 a concrete precondition ('Ask the user to confirm the subscription first') and a caution about re-activation. It never names a sibling alternative such as recurpay_skip_next_billing for a temporary pause, so the when-not path is left implicit.

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