Skip to main content
Glama

Hail Communication for AI

Read saved SMS application

get_sms_application
Read-onlyIdempotent

Read saved answers for an existing workspace registration.

    Returns private applicant fields, address and available sender information.
    An older application without saved answers returns 404.
    A number registration (``purpose="number"``) returns its kept answers,
    ``documents`` and the kept ``files`` by name (without their bytes) until
    ``kept_until``; ``resubmit_verification`` files it again from them.
    This read can recover an existing sender's details but creates no brand and files no campaign.
    Corrections retain the existing registration and its paid identity.

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>"
    },
    "name": "get_sms_application"
  }
}

Input Schema

NameRequiredDescriptionDefault
llm_modelNoModel ID of the calling agent. Optional. Recorded for analytics only.
verification_idYesID of the original registration, from ``list_verifications``: an SMS one, including one needing corrections, or a rejected number one.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / verification_id / description
      Previous value: -"ID of the original SMS registration, including one needing corrections, from ``list_verifications`` with purpose ``sms``."New value: +"ID of the original registration, from ``list_verifications``: an SMS one, including one needing corrections, or a rejected number one."
  2. Changed1 schema field changed
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "Model ID of the calling agent. Optional. Recorded for analytics only.",
      +  "type": "string"
      +}
  3. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses concrete behavior: 404 for older applications with no saved answers, files returned by name without bytes until kept_until, and an explicit statement of side effects that do not occur (no brand created, no campaign filed). The note that corrections retain the existing registration and its paid identity is a non-obvious consequence an agent could not derive from the schema.

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?

Purpose is front-loaded and each subsequent sentence adds a distinct behavior (return shape, 404, number registrations, non-effects). It is slightly over-stuffed for a two-parameter read, with formatting artifacts (indentation, doubled backticks) and a closing line about corrections that sits at the edge of relevance.

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 single-parameter read with an output schema, the description covers everything an agent needs: what comes back, the 404 case, the files-without-bytes detail, and an explicit statement of what the call does not do. Nothing about invoking it correctly is left to guesswork.

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%, and the schema already explains that verification_id comes from list_verifications and may be an SMS, corrections, or rejected-number registration. The description's registration-type discussion ('purpose="number"') mostly describes what is returned rather than adding new meaning to the parameter, so the baseline of 3 applies.

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

Purpose4/5

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

The opening sentence gives a specific verb and resource ('Read saved answers for an existing workspace registration') and the closing sentences bound the scope ('creates no brand and files no campaign'), which separates it from creation-oriented siblings. It does not explicitly distinguish itself from amend_sms_application or get_verification, so an agent must still infer the boundary against those reads.

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 when to reach for this read (recovering an existing sender's details, inspecting a number registration's kept answers) and routes one adjacent action to a named sibling ('resubmit_verification files it again from them'). It also flags a failure mode ('An older application without saved answers returns 404') that affects when the call is worthwhile. It stops short of saying when to prefer amend_sms_application or get_verification instead.

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