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

Annotations already declare readOnlyHint=false, idempotentHint=true, openWorldHint=true and destructiveHint=false, and the description adds value beyond them: the link is stable and reusable 'up to 3 days', nothing is billable, the call 'connects nothing by itself', and the human must sign in to Facebook as a Meta Business admin and verify the number. That resolves the main ambiguity of a non-read-only tool that does not itself mutate state.

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?

The link-producing action and the line-selection rule are front-loaded, and every sentence carries information (auth, idempotency window, billing, follow-up tool). Some sentences chain several clauses with semicolons and colons, which makes it denser than necessary, but nothing is 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?

Because an output schema exists, the description needn't document the return value, and it correctly focuses on prerequisites, eligibility, idempotent reuse, and the handoff to get_whatsapp_status. For a two-parameter, non-destructive onboarding tool, an agent has everything needed to call it correctly and interpret the result.

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?

With only 50% schema coverage and no description on business_id, the description compensates by explaining what phone_number means operationally: the default is the oldest KaiCalls line, and an override must be 'another of its lines'. business_id's role is only implied via 'the business's Meta Business account', so it stops short of full coverage.

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 and resource: 'Get the one link a business owner opens to put WhatsApp on their KaiCalls number.' It also implicitly separates itself from get_whatsapp_status by naming that tool as the reporting step, so an agent can distinguish the two without opening either schema.

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 explicit eligibility ('Owner or admin only'), the default targeting rule ('Uses the business's oldest KaiCalls line unless phone_number names another of its lines'), and the alternative/reporting path ('get_whatsapp_status reports the connection after the owner finishes'). This is when-to-use plus when-to-look-elsewhere guidance in a single pass.

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