Skip to main content
Glama

Update toll free verification

update_toll_free_verification
Destructive

Change a toll-free verification: send only the fields to change. Allowed while draft, in_review (until it goes to the carriers) and rejected; after a rejection, fix what it asks for, then submit again.

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": {
      "id": "<id>"
    },
    "name": "update_toll_free_verification"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesToll-free verification id (tfv_...)
einNoThe EIN (US), matching the legal name; elsewhere the business registration number.
cityNoCity.
stateNoState or province code.
streetNoStreet address of the business.
countryNoCountry of the business.
numbersNoYour live toll-free numbers this program texts from, E.164. One per business unless multiple_numbers_reason says why.
websiteNoThe business's website.
use_caseNoWhat the texts are for.
terms_urlNoThe terms page, with the SMS program terms.
help_replyNoThe reply to HELP: names the business and how to reach it. Omit to keep ours.
opt_in_urlNoThe opt-in page. With none of your own we make you a hosted one.
stop_replyNoThe reply to STOP: names the business and says they are unsubscribed. Omit to keep ours.
advertisingNoWhether the messages advertise a product or service.
brand_emailNoThe business's own email, for its customers: the HELP reply and the hosted opt-in page name it.
entity_typeNoThe kind of business.
fortune_500NoThe company is in the Fortune 500.
postal_codeNoZIP or postal code.
privacy_urlNoThe privacy policy page.
volume_basisNoexisting: what it sends today. projecting: an estimate.
business_nameNoThe legal name, as on the IRS EIN letter, optionally with "d/b/a" and the brand your messages carry.
contact_phoneNoA phone number they answer.
monthly_volumeNoHow many texts a month this program sends.
sample_messagesNoAt least two example messages.
number_publishedNoWhere people see this number.
previous_contentNoSample messages from the previous service (not new only).
previous_numbersNoThe numbers it used (not new only).
previous_serviceNoWhere this traffic ran before.
urls_in_messagesNoLinks your messages include, or "None".
use_case_summaryNoWhat the program sends, to whom and why. At least 40 characters.
contact_last_nameNoTheir last name.
contact_first_nameNoFirst name of the person the carriers can contact about this program.
opt_in_descriptionNoHow people opt in, step by step. At least 40 characters.
phones_in_messagesNoPhone numbers your messages include, or "None".
opt_in_screenshot_urlNoA public image of the step where people enter their number and agree. Needed when the opt-in page itself has no phone field, like a later step of a form or an app.
multiple_numbers_reasonNoWhy the program needs more than one number (one per store, say). Required with more than one number.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / opt_in_screenshot_url
      Added value: +{
      +  "description": "A public image of the step where people enter their number and agree. Needed when the opt-in page itself has no phone field, like a later step of a form or an app.",
      +  "format": "uri",
      +  "type": "string"
      +}
  2. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false; the description adds the state machine that governs when the call succeeds, which is real behavioral context not in the annotations. It also notes field-level defaults ("Omit to keep ours" for help_reply/stop_reply), though it does not say what is overwritten or what state the verification lands in after an edit.

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

Conciseness5/5

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

Two sentences, no filler, and the most action-shaping instruction (partial update) is front-loaded before the eligibility rules. Every clause carries information an agent needs before calling.

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 36-parameter mutation with no output schema, the description covers the two things the schema cannot: partial-update semantics and lifecycle preconditions. What remains unstated is the post-call effect (does the record return to draft, is re-review triggered) and what destructiveHint applies to.

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 36 parameters at 100% schema coverage, the baseline is 3, but the description adds the crucial PATCH contract — only send the fields you want changed — which changes how an agent should populate the schema. That single sentence materially reduces the risk of blanking out 35 optional fields.

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?

"Change a toll-free verification: send only the fields to change" gives a specific verb (change) plus resource, and the patch semantics distinguish it from a full create/replace. It implicitly points at a separate submit step ("then submit again") but never names submit_toll_free_verification or get_toll_free_verification, so differentiation from siblings is inferential rather than explicit.

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?

Unusually concrete eligibility rules: allowed while draft, in_review until the record goes to the carriers, and rejected, plus the post-rejection workflow of fixing what was flagged and resubmitting. The when-not condition (in_review after carrier submission) is stated, though the follow-up action is described generically as "submit again" instead of naming the sibling tool.

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.