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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is partially covered. The description genuinely adds beyond them by stating what does NOT happen (no carrier settings change, no number purchase, no phone call), which is useful scope-limiting context for a write tool. It still omits permissions/auth needs, what is actually created, and the multi-step workflow implied by the `step` enum.

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?

Three short sentences with no filler, and the negative-scope statement is placed early. The wording is tight, though the leading "Manage" verb creates ambiguity rather than earning its place.

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 10-parameter mutation tool with no output schema and only 30% schema coverage, the description leaves major gaps: the step-based workflow, the required idempotency key, what the call returns, and whether the setup must be completed across multiple invocations. What is present is accurate but far from sufficient.

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?

Only 30% of the 10 parameters carry schema descriptions, so the description is expected to compensate and it does not — no parameter is mentioned by name. Critical semantics such as the required `idempotency_key`, the `step` lifecycle, and the relationship between `source_number`, `number_id`, and `project_id` are left entirely to the sparse 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?

"Manage an existing-number forwarding setup" identifies the resource (existing-number forwarding) and scopes it away from carrier/number-purchase actions, but the verb "Manage" conflicts with the tool name "create" and with the existence of a sibling `update_forwarding_setup`. An agent cannot tell from the description whether this creates a new setup or mutates an existing one.

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?

There is no when-to-use guidance, no routing to `update_forwarding_setup`, `get_forwarding_setup`, `start_forwarding_test`, or `record_forwarding_instructions`, and no explanation of when the `step` values (setup/line/connect/test/manage) should be used. The only conditional hint is "Test verification requires linked call evidence," which is too fragmentary to guide invocation.

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