Modify a subscription

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

Annotations mark destructiveHint=true and idempotentHint=false, and the description amplifies this by specifying concrete side effects: 'may notify recipients or change tenant data'. It also discloses the operator write opt-in requirement and the form-change restriction, going well beyond what annotations alone convey.

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 but information-dense: endpoint, body fields, a disallowed mutation, prerequisites, side effects, and a reference link. It front-loads the core action and then packs essential constraints efficiently, though a bulleted list could improve scannability.

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 mutating endpoint with no output schema, the description covers the endpoint, required fields, disallowed changes, preconditions, and side effects. It doesn't describe the response shape, which could matter, but the reference link and the detail provided make it sufficiently complete 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?

Although schema description coverage is 100%, the body parameter is a generic object with additionalProperties, so the description's enumeration of body fields (id, name, description, owner, notificationDelay, criteria, recipients, targetAllDevices, targetDeviceNames) adds real semantic value. The confirm parameter is also explained in the schema, but the description's linkage to operator opt-in enriches it.

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 ('Modify') and resource ('a subscription'), reinforced by the exact HTTP endpoint (POST /api/xm/1/subscriptions). It clearly differentiates from sibling tools like create/delete/get subscriptions via the modify verb and endpoint, and the body field list adds specificity.

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 context: 'Include id and changed fields' tells the agent how to call it, 'The reference explicitly disallows changing form on an existing subscription' imposes a clear exclusion, and 'Requires operator write opt-in and confirm:true' adds a precondition. It doesn't name alternative sibling tools, but the constraints and prerequisites effectively narrow selection.

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