create_carrier_subscriber

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

With no annotations, the description carries the full burden. It discloses that this is a guarded write, requires a feature gate, and states that the tool is not testable against live hardware—only hermetic/spec-conformance tested, so a live create is impossible. This is valuable context beyond basic parameter docs, though it stops short of describing error responses or idempotency.

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 front-loaded with purpose and organized, but it redundantly lists parameters twice: once in prose ('subscriber_number is required...') and again at the end as a bullet-like series. Trimming that duplication would make it tighter without losing meaning.

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 the tool has 9 parameters, zero annotations, and an output schema, the description covers all necessary invocation details: the confirm gate, feature gate, testing limitations, every parameter constraint, and the key_label special case. An agent has everything required to call this tool correctly.

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 0%, and the description compensates fully. It explicitly documents every parameter: required subscriber_number (1-32 chars), length limits for name/email/notes/service_address, plan_id as UUID, metadata as object, confirm must be true, and key_label for API-key routing. This is exactly what an agent needs and goes far beyond the bare 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?

The description states a specific verb and resource: 'Create a Carrier / ISP Fabric subscriber (POST /v1/carrier/subscribers)'. It also adds 'Guarded write', which distinguishes this creation tool from other subscriber operations like update, suspend, attach, or detach that exist in the sibling list.

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 clear context for when to use the tool: creating a new subscriber, requiring confirm=true and the UNIFI_ENABLE_CARRIER_FABRIC_WRITE gate. It also notes that live creation is impossible in this environment. However, it does not explicitly name alternative tools for different operations, though the sibling names make the distinction obvious.

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