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

Annotations already signal not read-only and idempotent true; the description adds genuinely useful behavior: approval-gating, that it does not claim customer coverage, that the number is not fully set up until forwarding/owner phone are verified. This goes beyond the flag values.

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?

Every sentence carries distinct information: approval flag, precondition + action, downstream effect, and caveat with related tools. No filler.

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?

The description covers approval state, prerequisites, side effects, and what it does NOT do (claim customer coverage). Given the output schema and annotations, most operation-level context is present; the main gap is richer parameter semantics.

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 very low (only source_phone is self-explanatory). The description clarifies the meaning of the choice values (forwarding/published_number/both/testing), but leaves key parameters like business_id, activation_session_id, idempotency_key, and authority unexplained. The description does not sufficiently compensate for the schema's gaps.

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 names the exact action ('save forwarding, published_number, both, or testing') and the concrete consequence ('unlocks the command center'). It is clear that this is a configuration/selection operation, not a validation step, and it distinguishes the tool from later verification steps.

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?

It states a precondition ('after setup proof is complete'), warns about approval gating, and points to get_activation_status/set_owner_phone for verification. It does not explicitly say 'use this when X, otherwise use sibling Y,' but the guidance is sufficient for basic routing.

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