ls_update_subscription

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

The description adds meaningful behavioral context beyond the annotations: it discloses that payment-affecting updates are 'treated as destructive (rate-limited and audited)' and identifies which operations are not destructive. This refines the broad destructiveHint=true annotation with operation-level nuance.

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?

The description is two sentences, front-loaded with the core purpose, and each clause earns its place by adding usable distinctions. It packs parameter groupings, destructive classification, and an explicit sibling alternative without unnecessary filler.

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?

Given an 8-parameter update tool with no output schema and rich annotations, the description covers the key usage caveats and operation-level risks. Minor gaps remain, such as not explaining the interaction between disableProrations and variantId, but the combination of 100% schema coverage, annotations, and the description is largely sufficient for correct invocation.

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 is 3, but the description adds semantic value by grouping parameters according to their effect on payment: pause:'void'/'free' and variantId are destructive, while pause:'resume' and cancelled:false are not. It also maps high-level intent ('plan switch', 'pause/unpause') to the relevant parameter names, going beyond the schema's property descriptions.

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 the verb and resource ('Update a subscription') and enumerates the specific operations it supports: variant switch, pause/unpause, billing anchor, and invoice detail updates. It is clearly differentiated from the sibling ls_cancel_subscription, explicitly pointing cancellation to that tool.

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 description gives explicit usage guidance by classifying operations into destructive versus non-destructive groups: pausing, switching plans, changing billing anchor, invoicing immediately, and changing trial end alter payment and are rate-limited/audited; resuming, un-cancelling, and proration disabling are not. It also explicitly routes cancellation to ls_cancel_subscription.

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