create_subscription

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

No annotations are provided, so the description carries the disclosure burden. It does disclose the two most material behaviors — automatic recurring charges and the token prerequisite — but omits other facts relevant to a money-moving tool: whether the first charge is immediate, the two-step auth/confirm flow implied by RequireConfirmation, and failure/reversibility behavior.

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?

Three short sentences with zero filler. The primary action is front-loaded, and each subsequent sentence adds a distinct fact: the prerequisite, then the behavioral consequence of automatic charging.

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 an 11-parameter financial tool with no annotations and no output schema, a two-sentence description is thin. Missing guidance includes what the response contains, whether StartDate triggers an immediate debit, and the confirmation workflow when RequireConfirmation=true — gaps an agent cannot safely infer when setting up recurring charges.

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 the schema already documents all 11 parameters, including the Token source (Transaction.Token) and currency default. The description adds modest context by explaining why the token is required, but it does not compensate for anything the schema lacks, so the 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?

The description states a specific verb ('Create') and a specific resource ('recurring subscription'), and reinforces scope with 'Charges automatically on schedule.' This distinguishes it from one-off payment siblings like charge_payment and from the subscription lifecycle siblings (update_subscription, cancel_subscription, list_subscriptions) without requiring the agent to open 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?

The prerequisite is explicit: 'Requires a token from a previous payment,' which tells the agent this tool is only callable after a payment step has produced a token. It provides clear context for when to invoke it, but does not explicitly name alternatives or state exclusions (e.g., when to prefer charge_payment for one-time charges or update_subscription for modifying an existing plan).

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