Create a subscription

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

The annotations already indicate destructiveHint=true and idempotentHint=false. The description adds meaningful context beyond that by noting 'may notify recipients or change tenant data' and requiring 'operator write opt-in and confirm:true'. This gives the agent a clearer picture of the mutation's impact, surpassing what annotations alone provide.

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 compact and front-loads the action and endpoint, followed by the body fields, reference link, and requirements. It packs useful information without unnecessary verbosity, though the list of fields and caveats makes it slightly dense.

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 complex create operation, the description covers the endpoint, body fields, required confirm flag, permission requirement, and side effects. It also provides a reference link for deeper details. While it doesn't detail nested structures or response format, the provided information is sufficient for an agent to make a correct call in most cases.

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?

The schema descriptions are 100% coverage, but the description goes further by enumerating the key body fields (name, description, form, owner, notificationDelay, criteria, recipients, targetDeviceNames) that are not detailed in the generic 'Complete API JSON payload' schema description. This adds practical value for constructing the payload.

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 clearly states the action ('Create a subscription') and the specific resource (subscriptions via POST /api/xm/1/subscriptions). It lists the body fields, making it unambiguous what the tool does and distinguishing it from other subscription operations like modify or delete.

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 provides some context (requires operator write opt-in and confirm:true) and warns about side effects, but it does not explicitly state when to use this tool versus alternatives (e.g., modify or delete subscription). The guidance is implied by the tool name and action but not spelled out.

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