Skip to main content
Glama

Reuse a verification number

reuse_number
Destructive

Receive another SMS on an earlier verification's number, free or paid, after checking reuse flags and price via get_rental.

Instructions

Receive another SMS on the number of an earlier verification (ver_...). Free reuse: when allow_reuse is true. Paid reuse (paid=true): when allow_paid_reuse is true; charges paid_reuse_price_cents, refunded automatically if the number is no longer available, and requires max_price_cents (that price, shown to and approved by the user). Check both flags and the price with get_rental first, then call get_rental with wait_seconds for the new code.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paidNo
rental_idYesver_... id of an earlier verification
max_price_centsNoRequired when paid=true: the paid_reuse_price_cents you showed the user and they approved, in US cents. Refused uncharged if the price is higher.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
verificationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.1
    • addedInput schema / properties / max_price_cents
      Added value: +{
      +  "description": "Required when paid=true: the paid_reuse_price_cents you showed the user and they approved, in US cents. Refused uncharged if the price is higher.",
      +  "exclusiveMinimum": 0,
      +  "maximum": 1000000,
      +  "type": "integer"
      +}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "properties": {
      +    "verification": {
      +      "additionalProperties": {},
      +      "properties": {
      +        "allow_paid_reuse": {
      +          "type": "boolean"
      +        },
      +        "allow_reuse": {
      +          "type": "boolean"
      +        },
      +        "can_cancel": {
      +          "type": "boolean"
      +        },
      +        "charged_price_cents": {
      +          "maximum": 9007199254740991,
      +          "minimum": -9007199254740991,
      +          "type": "integer"
      +        },
      +        "charged_reuse_cents": {
      +          "maximum": 9007199254740991,
      +          "minimum": -9007199254740991,
      +          "type": "integer"
      +        },
      +        "code": {
      +          "type": "string"
      +        },
      +        "code_received_at": {
      +          "type": "string"
      +        },
      +        "created_at": {
      +          "type": "string"
      +        },
      +        "display_id": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "expires_at": {
      +          "type": "string"
      +        },
      +        "id": {
      +          "type": "string"
      +        },
      +        "paid_reuse_price_cents": {
      +          "maximum": 9007199254740991,
      +          "minimum": -9007199254740991,
      +          "type": "integer"
      +        },
      +        "phone_number": {
      +          "type": "string"
      +        },
      +        "refunded_cents": {
      +          "maximum": 9007199254740991,
      +          "minimum": -9007199254740991,
      +          "type": "integer"
      +        },
      +        "reuse_counter": {
      +          "maximum": 9007199254740991,
      +          "minimum": -9007199254740991,
      +          "type": "integer"
      +        },
      +        "service_id": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "service_name": {
      +          "type": "string"
      +        },
      +        "status": {
      +          "enum": [
      +            "waiting_for_code",
      +            "code_received",
      +            "cancelled",
      +            "expired",
      +            "failed"
      +          ],
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "id",
      +        "status",
      +        "phone_number",
      +        "service_id",
      +        "service_name",
      +        "charged_price_cents",
      +        "expires_at",
      +        "can_cancel",
      +        "created_at",
      +        "reuse_counter",
      +        "allow_reuse",
      +        "allow_paid_reuse",
      +        "paid_reuse_price_cents"
      +      ],
      +      "type": "object"
      +    }
      +  },
      +  "required": [
      +    "verification"
      +  ],
      +  "type": "object"
      +}
  2. Changed2 schema fields changedv1.1.8
    • changedInput schema / properties / rental_id / description
      Previous value: -"ver_xxx from a verification"New value: +"ver_... id of an earlier verification"
    • addedInput schema / properties / rental_id / pattern
      Added value: +"^(?:ver_[A-Za-z0-9_-]{1,64})$"
  3. First observedv1.1.3

TDQS

A4.5/5.0
Behavior4/5

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

Adds substantive behavior beyond the annotations: billing (paid_reuse_price_cents), automatic refund when the number is unavailable, and the requirement that max_price_cents reflect a user-approved price. It does not restate destructiveHint=false-style facts, and it does not contradict the declared destructive/openWorld profile. It stops short of discussing idempotency or concurrency for a non-idempotent, billable action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: the core action comes first, then the free/paid branches, then the required get_rental sequencing. It is a single run-on paragraph with one slightly awkward repeated reference to get_rental, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a billable, destructive operation with an output schema (so return values need no explanation), the description covers cost, refund, approval, flags, and the get_rental prerequisite. Minor gaps: no statement of failure modes beyond price-too-high, and no mention of idempotency in the face of retries.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema coverage at 67%, the description compensates well: it ties paid=true to allow_paid_reuse, explains that max_price_cents is a user-approved ceiling, and identifies rental_id as a ver_... id of an earlier verification. It adds conditional logic the schema cannot express, though exact price-lookup syntax remains in get_rental.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+scope: 'Receive another SMS on the number of an earlier verification (ver_...)'. It is clearly distinguishable from siblings like rent_number (new rental) and get_rental (status check), and it splits the operation into free vs. paid paths up front.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit preconditions ('when allow_reuse is true', 'when allow_paid_reuse is true') and an explicit workflow with the sibling tool: 'Check both flags and the price with get_rental first, then call get_rental with wait_seconds for the new code.' No inference required.

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