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

The annotations already declare readOnly=false, destructive=false and openWorld=false; the description adds genuinely new information by ruling out three concrete side effects (carrier settings changes, number purchase, phone call) and by stating a verification dependency on linked call evidence. It omits other important behavior: nothing explains why an idempotency_key is mandatory while idempotentHint=false, nor what base_revision concurrency semantics apply, nor what authorization is required.

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, but the opening sentence is the least informative and leads with the generic verb 'Manage' rather than the test action. The negative scoping ('No carrier settings change...') earns its place; the middle sentence structure is serviceable but not front-loaded around what the tool does.

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 tool with four required parameters, no output schema and zero schema descriptions, the description is thin but not empty — it establishes that this acts on an existing setup and produces no external carrier effect. It still leaves the agent unclear on what a 'started test' returns, what happens after starting, and how the required revision/idempotency parameters must be supplied.

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% across five parameters, and the description supplies no parameter meaning at all — setup_id, condition, project_id, base_revision and idempotency_key are never mentioned. base_revision (optimistic concurrency) and idempotency_key (retry safety) are non-obvious and would have been the highest-value items to explain, and their conflict with idempotentHint=false goes unaddressed.

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 frames the tool as 'Manage an existing-number forwarding setup', which is broader and vaguer than the title's 'Start forwarding test' — the actual action (initiating a test run) is never stated with a verb. It does usefully narrow the resource to an already-existing setup, which separates it from create_forwarding_setup, but an agent could not distinguish it from get_forwarding_test or cancel_forwarding_test on the description alone.

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 explicit when-to-use guidance, no when-not-to-use guidance, and no sibling tool is named as an alternative (get_forwarding_test, cancel_forwarding_test, update_forwarding_setup all compete here). The clause 'Test verification requires linked call evidence' hints at a precondition for verification, but it is oblique and does not tell the agent when to call this versus inspecting an existing test.

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