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

Annotations only declare destructiveHint/idempotent flags; the description adds the state machine (pause needs active, resume needs paused, cancel works on either), the irreversibility of cancel, and the exact error behavior (unknown id or status mismatch returns an error and changes nothing) plus the return value.

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?

It is a single dense paragraph, but it is front-loaded with the gating condition and every clause (state requirements, error semantics, sibling routing) carries information. Slightly long, though nothing is redundant.

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 state-changing tool with 2 fully documented params and an output schema, the description covers preconditions, allowed transitions, failure modes, and return behavior. An output schema exists, so it correctly does not need to enumerate return fields.

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 baseline would be 3, but the description adds meaning beyond the schema: subscription_id must come from my_subscriptions and ids from other accounts are never found, which is cross-account scoping not present in 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?

The description names a specific verb+resource (change one of their tea subscriptions) and enumerates the exact operations (pause, resume, cancel) so the agent can immediately distinguish it from siblings like my_subscriptions or update_basket.

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 states the triggering condition (signed-in customer clearly asks), the prerequisite confirmation step, and routes the agent to my_subscriptions for discovery first. It also implies when not to use it: unknown ids or status-mismatched changes fail and change nothing.

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