Configure a phone number

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint. The description adds genuinely non-obvious behavior: the mutual exclusion between application and trunk linkage, the feature-flag gate VOBIZ_ENABLE_PROVISIONING, and the mandatory confirm gate. It does not describe what happens to existing tags on replace or the error shape.

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?

Two tight sentences, front-loaded with the operation set and scope. Every clause carries information, though the mutual-exclusion rule and the gating/confirm note are somewhat compressed into the back half.

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 7-param mutation tool with no output schema, the description covers scope, the main operation modes, the exclusivity constraint, and the two safety gates. An agent has enough to call it correctly; only failure/return semantics and the phone_number argument are inferred.

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 only 29% across 7 params, so the description must compensate, and it largely does, explaining tags replacement, application linking semantics (inbound calls run that app's answer_url), trunk linking, and the unlink variants. Only phone_number itself is left to the regex pattern in the 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?

States a specific verb (change configuration) and resource (one owned number), then enumerates the actual operations: replace tags, link to an application, link to a SIP trunk, or unlink. This clearly separates it from update_sip_trunk, update_application, and assign_number_to_subaccount.

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?

Gives clear conditions for use (linking/unlinking an owned number) and a hard constraint: a number can be linked to an application OR a trunk, not both. It also names the gating flag and confirm requirement. It stops short of explicitly routing the agent away from sibling tools like update_sip_trunk, so it is strong but not exhaustive.

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