Skip to main content
Glama

Hail Communication for AI

Correct an existing SMS application

amend_sms_application
DestructiveIdempotent

Correct an existing SMS registration at the needs_information step.

    The address must be accurate; saved details can be reused when still correct.
    Identity changes are rejected. This operation does not create a replacement brand.
    Actual consent evidence is required.
    Limits are 100 fields and 64 KiB of combined fields and address. No documents are uploaded.
    A later campaign filing can incur the normal review fee.
    After a timeout, the existing registration can already reflect the correction.
    Returns the updated registration or an error.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "verification_id": "<verification_id>",
      "fields": "<fields>",
      "attest_authorized": "<attest_authorized>"
    },
    "name": "amend_sms_application"
  }
}

Input Schema

NameRequiredDescriptionDefault
fieldsYesComplete corrected answers that satisfy the current requirements; ``get_sms_application`` returns the saved ones.
addressNoThe sender's original address, as saved; ``get_sms_application`` returns it. Omitted: the correction is refused, because Hail cannot confirm the sender is unchanged.
llm_modelNoModel ID of the calling agent. Optional. Recorded for analytics only.
verification_idYesID of the SMS registration at step ``needs_information``, from ``list_verifications``; the same paid application and identity.
attest_authorizedYes``true`` records that the applicant reviewed and approved these corrections.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / address / anyOf
      Previous value: -[
      -  {
      -    "properties": {
      -      "city": {
      -        "description": "City or locality.",
      -        "title": "City",
      -        "type": "string"
      -      },
      -      "country_code": {
      -        "description": "ISO alpha-2 address country.",
      -        "title": "Country Code",
      -        "type": "string"
      -      },
      -      "customer_name": {
      -        "description": "Name associated with the address.",
      -        "title": "Customer Name",
      -        "type": "string"
      -      },
      -      "postal_code": {
      -        "description": "Postal or ZIP code.",
      -        "title": "Postal Code",
      -        "type": "string"
      -      },
      -      "region": {
      -        "description": "State, province or region.",
      -        "title": "Region",
      -        "type": "string"
      -      },
      -      "street": {
      -        "description": "Street address.",
      -        "title": "Street",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "customer_name",
      -      "street",
      -      "city",
      -      "region",
      -      "postal_code",
      -      "country_code"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "properties": {
      +      "city": {
      +        "description": "City or town of the street address, as written on mail sent there.",
      +        "title": "City",
      +        "type": "string"
      +      },
      +      "country_code": {
      +        "description": "ISO alpha-2 address country.",
      +        "title": "Country Code",
      +        "type": "string"
      +      },
      +      "customer_name": {
      +        "description": "Name associated with the address.",
      +        "title": "Customer Name",
      +        "type": "string"
      +      },
      +      "postal_code": {
      +        "description": "Postal or ZIP code of the street address, such as `94103`.",
      +        "title": "Postal Code",
      +        "type": "string"
      +      },
      +      "region": {
      +        "description": "State, province or region.",
      +        "title": "Region",
      +        "type": "string"
      +      },
      +      "street": {
      +        "description": "Street address.",
      +        "title": "Street",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "customer_name",
      +      "street",
      +      "city",
      +      "region",
      +      "postal_code",
      +      "country_code"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / attest_authorized / description
      Previous value: -"Attestation that the applicant reviewed and authorized the corrections. Only ``true`` is accepted."New value: +"``true`` records that the applicant reviewed and approved these corrections."
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "Model ID of the calling agent. Optional. Recorded for analytics only.",
      +  "type": "string"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / address / anyOf
      Previous value: -[
      -  {
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "properties": {
      +      "city": {
      +        "description": "City or locality.",
      +        "title": "City",
      +        "type": "string"
      +      },
      +      "country_code": {
      +        "description": "ISO alpha-2 address country.",
      +        "title": "Country Code",
      +        "type": "string"
      +      },
      +      "customer_name": {
      +        "description": "Name associated with the address.",
      +        "title": "Customer Name",
      +        "type": "string"
      +      },
      +      "postal_code": {
      +        "description": "Postal or ZIP code.",
      +        "title": "Postal Code",
      +        "type": "string"
      +      },
      +      "region": {
      +        "description": "State, province or region.",
      +        "title": "Region",
      +        "type": "string"
      +      },
      +      "street": {
      +        "description": "Street address.",
      +        "title": "Street",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "customer_name",
      +      "street",
      +      "city",
      +      "region",
      +      "postal_code",
      +      "country_code"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / address / description
      Previous value: -"Applicant address with ``customer_name``, ``street``, ``city``, ``region``, ``postal_code`` and ``country_code``, when the requirements include one."New value: +"The sender's original address, as saved; ``get_sms_application`` returns it. Omitted: the correction is refused, because Hail cannot confirm the sender is unchanged."
  3. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, yet the description still adds substantive behavior: identity changes are rejected, no replacement brand is created, consent evidence is mandatory, there are hard limits of 100 fields and 64 KiB, no documents are uploaded, and a later campaign filing can incur a review fee. It also explains the timeout case (the correction may already be reflected), which is exactly the nuance an idempotent destructive write needs and which annotations alone cannot convey.

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?

The purpose sentence is front-loaded and each following line carries a distinct constraint (accuracy, rejected identity changes, consent evidence, size limits, fee, timeout). It is terse and scannable, though the limits/fee/timeout lines are dense enough that a reader must parse several unrelated facts in sequence.

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

Completeness5/5

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

For a destructive, open-world mutation with nested address objects, the description covers preconditions, what is and is not permitted, size caps, side effects (fee), timeout semantics and the return shape, while an output schema already exists to describe return values. An agent has everything needed to call it correctly and to anticipate the failure modes.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents verification_id, fields, address, attest_authorized and llm_model in detail, including the refusal when address is omitted. The description adds only the requirement that the address be accurate while other saved details may be reused, which reinforces rather than extends the schema; baseline 3 is appropriate.

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?

The description opens with a specific verb and resource ("Correct an existing SMS registration") and pins the exact lifecycle state ("at the needs_information step"). That distinguishes it cleanly from read-oriented siblings such as get_sms_application and preview_sms_application without the agent 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.

Usage Guidelines4/5

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

It states the precondition for calling (the registration must be at needs_information) and points to get_sms_application as the source of the saved fields and address to reuse. It also fences off adjacent intents by saying identity changes are rejected and no replacement brand is created, but it never names an alternative tool for those cases, so routing for out-of-scope requests is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources