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

Annotations flag destructive=true, idempotent=true, and readOnly=false; the description adds real context beyond that — the value replaces any earlier destination, the actual send happens later through the messaging provider, and saving is explicitly not proof of delivery. That last clause usefully prevents an agent from treating a successful call as confirmation of dispatch, though rate limits or failure modes are not covered.

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 tightly packed sentences, front-loaded with the APPROVAL-GATED gate and the core action, with no filler. The delivery-caveat sentence is long but earns its place by correcting a likely misinterpretation.

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?

An output schema exists so return values need no explanation, and the mutation semantics plus approval gate are covered. However, for a 6-parameter destructive write with 0% schema coverage and a nested 'authority' object, the description leaves too much of the call contract unexplained for an agent to invoke it confidently.

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 6 parameters, so the description must carry the load; it does explain channel (SMS vs email), destination (phone/email), and the session scoping, mapping to three of the required fields. It says nothing about business_id, the nested 'authority' object, or idempotency_key, leaving the most opaque parameters undocumented.

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 gives a specific verb ('Save') plus the precise resource ('the owner-approved phone number (SMS) or email address') and scopes it to 'the exact active activation session', so an agent knows this stores a notification destination rather than sending anything. It doesn't explicitly name sibling tools like retry_activation_notification or add_team_phone, but the destination-for-activation framing is distinct enough to route on.

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 clear prerequisite ('APPROVAL-GATED') and a clear scoping condition ('for the exact active activation session'), plus replacement behavior for prior values. It stops short of naming when NOT to use it or which sibling to call instead, so the routing is implied rather than spelled out.

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