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

Annotations already declare destructiveHint=true and non-idempotent, and the description adds substantial context beyond them: a retention offer step, an explicit confirmation gate ('makes it only after the customer replies yes'), an identity verification requirement (email plus postcode, or an EC order number), and what the reply contains. That is exactly the behavioral detail an agent needs before invoking a destructive tool.

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, then the retention/confirmation flow, then identity, then conversation mechanics and return value. Every sentence carries information, though the identity and conversationId sentences are dense and slightly interleaved rather than grouped.

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, multi-turn, stateful tool with no output schema, the description covers the confirmation protocol, identity gate, conversation continuity, and what the returned reply represents. Nothing essential to calling it correctly is missing.

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 0%, so the description carries the full burden and does most of it: message is defined as the customer's own words, and conversationId is explained as absent on the first call and returned by each result to continue the conversation. It does not explicitly say the identity details must be supplied within message, which is the one actionable gap.

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 (cancels the customer's IMPOSSIBREW subscription) and implicitly separates itself from pause_subscription and skip_next_delivery by naming discount/pause/skip as retention offers made before cancellation. An agent can tell what this tool does and what it is not without opening the schema.

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 clear triggering context (customer wants to cancel) and describes the required pre-cancellation flow, including that only an option the customer explicitly accepts is applied. It stops short of naming the sibling tools (pause_subscription, skip_next_delivery) as the destinations for those alternatives, so the routing is implied rather than explicit.

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