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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds genuinely useful context the annotations do not carry: the prepaid billing-interval behavior and the fact that an empty note_attributes list erases existing attributes. It does not address permissions, validation failure modes, or what happens to items when intervals change (other than the automatically_update_product_prices parameter's own schema text).

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 'WRITE:' marker and a single dense sentence that scopes the resource, followed by two short qualifier sentences. Nearly every clause carries information, though the parenthetical prepaid explanation slightly duplicates the billing_interval schema description.

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 23-parameter mutation with no output schema and low schema coverage, the definition gives an agent enough to pick the right fields and understand partial-update and deletion semantics. Missing details are secondary: response shape, behavior on invalid interval strings, and whether address changes affect future versus already-scheduled orders.

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?

With 23 parameters and only 30% schema description coverage, the description has to compensate, and it does by grouping the parameters into named domains (intervals, min/max payments, note attributes, delivery method and price, shipping address) and flagging the empty-list deletion semantics. The remaining gap is that the individual address fields, delivery_method_* variants, and interval string formatting are left to 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?

States a specific verb and resource ('Edit a subscription's schedule and details') and enumerates the editable field groups: intervals, payment cycles, note attributes, delivery method/price, and shipping address. It also explicitly excludes item changes by pointing to the item tools, which separates it from sealsubscriptions_edit_items and add_items.

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?

'Only the fields you pass change' establishes partial-update semantics clearly, and 'To change items use the item tools' routes the most likely confusion to a sibling. It stops short of naming which sibling to use for adjacent operations like pausing, rescheduling, or cancellation scheduling, so the exclusions are not complete.

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