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

Annotations declare a destructive, open-world, idempotent mutation, and the description fills in the substance behind those flags: a real phone call to a human, a 6-digit code read twice, a 10-minute validity window, and 24-hour deduplication of identical requests. What it omits is the cost/telephony side effect that plausibly justifies destructiveHint=true, and what happens on no-answer or wrong code.

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 core instruction is front-loaded and useful, but the idempotency guidance is stated twice in near-identical terms ('A retried identical call returns the same result; pass a new idempotencyKey...' then 'Identical requests are deduplicated for 24 hours; use a new idempotencyKey only...'), and it largely restates the idempotencyKey schema description. One consolidated sentence would carry the same information.

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 mutation with real-world side effects and no output schema, the description explains the flow and how the result is consumed downstream via ringkit_confirm_destination, which is the most important part. It does not indicate what the call returns (call id, status, code delivery state) or failure modes, leaving the agent without expectations about the response.

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?

The description makes clear that `number` is the destination being verified and expands on idempotencyKey semantics beyond the schema's own text (retries reuse it, new value deliberately repeats). businessId is already documented in the schema. With 67% schema coverage, the baseline of 3 applies; the addition over the schema is modest since two of three params are already described in structured fields.

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?

Specific verb and resource: place a verification call to `number` from the business's RingKit number and read a 6-digit code to prove ownership. The stated goal ('to prove the business controls it') is concrete. It does not distinguish itself from sibling call-placing tools like ringkit_test_call or ringkit_simulate_call, which is the only thing keeping it from a 5.

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?

The 'Step 8' framing and the explicit hand-off to ringkit_confirm_destination convey the workflow context, and the note about when to pass a new idempotencyKey ('only to deliberately repeat the action') is genuine usage guidance. However, there is no statement of when NOT to use this versus ringkit_test_call/ringkit_simulate_call, and no prerequisites such as a provisioned number being required.

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