sms-verify

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

With no annotations, the description carries the full burden and does so well: it discloses that prices are in credits, that values are approximate (typical mobile number, carrier variance), that data is refreshed at least daily via `checked_at` in UTC, and that billing is metered (~0.41 avg per request). It stops short of describing pagination or the full response shape, but the behavioral profile is unusually rich.

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 is front-loaded and earns its place: content first, then freshness caveat, then the sibling routing, then exclusions, then group and billing metadata. No filler or repetition of the name.

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?

There is no output schema and no annotations, so the description must supply everything, and it does: what is returned, in what unit, sorted how, how fresh it is, what is omitted, and the cost of calling it. An agent can call this correctly with no further information.

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 tool takes zero parameters, so per the rubric the baseline is 4. The description instead adds semantic meaning to the returned fields (credits, checked_at, per-country typical-number basis), which goes beyond an empty schema without being a parameter explanation.

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 states exactly what the tool returns — per-country credit pricing for verification SMS, sorted by country name — which is a specific resource and scope. It implicitly distinguishes itself from the cost-estimation sibling by noting that countries are priced for a 'typical mobile number' while 'Estimate Cost' gives an exact number.

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 names the alternative tool explicitly ('use Estimate Cost for an exact number') and gives the condition that selects it (carrier-level precision needed). It also states the exclusion rule — countries SMS cannot be sent to are omitted — so an agent knows what absence of a country means.

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

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

With no annotations, the description carries the full burden and does well: it declares no side effects ('Nothing is sent'), explains that cost varies by carrier and may diverge from the price list, and quantifies the billing profile ('0 Credits', 'metered ~0.36 avg'). It also explains the `null` region_code edge case.

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?

Front-loads the tool's output (cost in credits) before qualifiers, and every clause adds information. The trailing parentheticals are dense but not wasteful.

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?

With no annotations and no output schema, the description must cover both behavior and return shape; it does — return values (credits, region_code with null semantics), safety (nothing sent), and billing. Nothing needed to invoke it correctly is missing.

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 100% and the single `target` parameter's format is fully documented in the schema, so baseline 3 applies. The description adds meaning about the *result* (credits, region_code) rather than the input, which is useful but not parameter semantics.

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 precise outcome: the credit cost of a verification SMS to a given number, plus the number's country as `region_code`. It implicitly separates itself from `get_pricing` by noting the price is carrier-specific rather than the country-list price, so an agent can route correctly.

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 phrase 'Nothing is sent' clearly signals this is the dry-run counterpart to `post_send_numeric_verify`, which is the key usage decision. It stops short of naming the sibling or stating an explicit when-not rule, but the context is unambiguous.

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

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

No annotations exist, so the description carries the full burden and does so well: it discloses the exact message template, credit metering with an average cost, the 10,000-credit cap and its failure mode, and that failed requests are not charged. Gaps remain around rate limits, code TTL/expiry, and retry/idempotency behavior, which matter for a send operation.

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 action and the returned code are front-loaded, and each sentence carries substantive information about cost and failure. The trailing 'Group: Verification. Billing per call: Credits: metered (~518.21 avg)' partially restates the cost sentence, which is minor redundancy.

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?

With no annotations and no output schema, the description fills the critical gaps by explaining that the code is returned and what failures look like. It is nearly complete for a one-parameter tool, missing only code lifetime and rate-limit expectations for an SMS-sending operation.

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?

Only one parameter and schema coverage is 100%, so the schema already documents international format, separators, and the missing-plus behavior. The description repeats only 'phone number' without adding format or edge-case detail, so the baseline 3 applies.

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 (sends a six-digit SMS verification code to a phone number) and clarifies it also returns the code for comparison. The scope is narrow and unambiguous enough to distinguish it from get_pricing and post_estimate_cost without opening any 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?

Explains the usage context ('so you can compare it with what the user types') and states the failure condition where the send is blocked (max_cost_exceeded). It does not explicitly say when to prefer get_pricing or post_estimate_cost first, but that is inferable from the cost discussion.

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