Skip to main content
Glama
KaiCalls MCP Server

KaiCalls MCP Server

Official

Get Text Registration

get_text_registration
Read-onlyIdempotent

Read a business's carrier registration status for texting—filing stage, payment, sales-text permission, next step—and optionally run a pre-filing check to catch rejection issues before paying.

Instructions

Read where a business stands on its own carrier registration for business texting: saved details (never the EIN; only whether one is on file), payment, filing stage, whether sales texts are allowed, and the one next step. In MCP, known excludes fields the canonical flow still requires the owner to confirm; suggestions preserves those nonprivate values and available provenance. missing is the ordered outstanding field-question list, with missing_value or confirmation_required reasons; next_question is its first item. question_progress counts field questions including next, not website screens. Website screens group several fields and may include a private identity step; unequal counts can be valid. The MCP presentation separates configured registration/enrollment from recipient-specific sending permission and delivery, which remain not_checked. A null own registration does not prove an enrolled platform route cannot text; configured lines do not prove a send is authorized. Dashboard/API presentation is unchanged. Pass check=true to also run the pre-filing check: every problem a carrier reviewer would reject the registration on (business details, campaign wording, website, privacy policy, texting terms, opt-in page, the phone opt-in script), each as prefiling_check.items with a plain fix, so it can be fixed before anything is paid. Read-only.

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": {
      "business_id": "<business_id>"
    },
    "name": "get_text_registration"
  }
}

Input Schema

NameRequiredDescriptionDefault
checkNoAlso run the pre-filing check and return prefiling_check (ready, items with title and fix).
business_idYes

Output Schema

NameRequiredDescriptionDefault
addonNo
errorNoPresent when success is false
knownNo
chasersNo
missingNo
successYesWhether the tool completed successfully
deliveryNo
next_stepNo
setup_urlNo
ein_on_fileNo
suggestionsNo
registrationNo
textingLinesNo
account_routeNo
next_questionNo
next_step_textNo
prefiling_checkNo
recipient_checksNo
question_progressNo
sending_permissionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations, the description discloses meaningful behavior: the EIN is never returned (only whether one is on file), 'not_checked' marks recipient-specific sending permission and delivery, and it warns that a null registration does not prove an enrolled route cannot text and that configured lines do not prove a send is authorized. These are genuinely useful non-obvious caveats; it loses a point for not stating any freshness/caching or failure behavior.

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 is front-loaded in the first sentence and key constraints are stated, but the middle is dense with return-field pedagogy (question_progress, website screens, missing/next_question) that duplicates an output schema. Clauses like 'Dashboard/API presentation is unchanged' do no work for an agent deciding to call the tool.

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 two-parameter read tool with an output schema and full safety annotations, the definition is more than sufficient: it covers the default read mode, the optional check mode, the privacy limit on EIN, and the null/not_checked interpretation pitfalls. Only the required business_id remains unexplained.

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?

business_id is undocumented in both schema and description (50% coverage), and its purpose is only inferable from the tool's scope. The check parameter is partly covered by the schema and expanded in the description ('prefiling_check.items with a plain fix'), but the description's effort is spent on return-field semantics rather than input semantics.

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 where a business stands on its own carrier registration for business texting,' and enumerates what is returned (saved details, payment, filing stage, sales-text permission, next step). It never names or contrasts a sibling (e.g., get_channel_status, get_business_verification, save_text_registration_details), so an agent must infer the boundary itself.

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

Usage Guidelines3/5

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

Usage is implied by 'Read' and 'Read-only,' and the optional mode is well framed: 'Pass check=true to also run the pre-filing check... so it can be fixed before anything is paid,' which tells the agent when the flag matters. However, there is no explicit when-to-use guidance versus sibling status tools, and no statement of when not to use this tool (e.g., before a registration exists).

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

Deploy Server

Other Tools