Skip to main content
Glama

Recheck registration

recheck_registration
Destructive

Correct a registration and run its checks again (draft, checks_failed, ready or rejected). Send any field to change it; after fixing the website, this re-reads it. Returns the new status and findings.

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>",
      "business_name": "<business_name>",
      "website": "<website>",
      "use_case": "<use_case>"
    },
    "name": "recheck_registration"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesRegistration id (reg_...)
brandNoThe business as the carriers register it. street must be a street address, not a P.O. box; state a 2-letter US state or territory code; postal_code a 5-digit ZIP (optionally +4). Anything else is refused with 400 naming the field.
websiteYesThe business's own website. Reviewers visit it to confirm the business is real.
use_caseYesWhat the texts are for. marketing and mixed need an opt-in for each person.
age_gatedNoYour messages are for adults only (alcohol, cannabis, gambling).
terms_urlNoDiscovered from homepage links when omitted
help_replyNoYour wording of the HELP reply. It must name your business, give a way to reach you (email, phone or web page) and keep the STOP instruction. Omit or null for the standard wording.
opt_in_urlNoPage where people enter their number
stop_replyNoYour wording of the confirmation sent when someone opts out. It must name your business, say they are unsubscribed, and carry no link; anything else is a 400 naming what is missing. Omit or null for the standard wording in your business name. Filed with the registration and sent by its numbers.
descriptionNoWhat you send and to whom (40 to 500 characters). Omit or null to file the generated one.
opt_in_flowNoHow people opt in, in your own words. It leads the filed opt-in account; the opt-in page, the disclosure and the START keyword are added after it. Omit or null to file the standard sentence.
privacy_urlNoDiscovered from homepage links when omitted
business_nameYesThe name customers know the business by, as the texts will name it.
support_emailNoUsed in the generated HELP reply
direct_lendingNoYour messages are about loans you make yourself.
includes_linksNoYour messages include web links. Also true whenever an example contains one.
sample_messagesNoReal examples of the texts you will send, as a recipient would get them (no template variables). Carriers compare them with your traffic. Each must name your business; marketing and mixed use cases need opt-out wording in at least one. More than 5, or one over 320 characters, is a 400; too few or too short comes back as findings. Omit to get starter drafts; null or [] goes back to them.
starter_messagesNoDraft examples suggested for this business (fields.sample_messages from POST /registrations/prefill). Shown instead of the template starter drafts; samples_source stays starter and they are never filed until you edit or confirm them. Drafts that would not pass the example check for the business name and use case are ignored.
samples_confirmedNotrue = the starter drafts are right as they are; they become your examples. Ignored when sample_messages is sent.
opt_in_screenshot_urlNoPeople opt in inside an app: a public link to an image of that screen. Checked in place of a phone field and filed with the opt-in. null clears it.
includes_phone_numbersNoYour messages include phone numbers. Also true whenever an example contains one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already state destructiveHint=true, idempotentHint=false and openWorldHint=true, so the mutation and non-idempotency profile is covered structurally. The description adds that the website is re-read and that the response carries the new status and findings, but it does not explain what a re-check overwrites, whether prior findings are discarded, or what external lookups the re-check triggers.

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?

Three short sentences, each doing distinct work: purpose plus applicable states, partial-update semantics, then return shape. Nothing is repeated from the title and the key constraint is front-loaded.

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 21-parameter nested-schema mutation with no output schema, the description covers purpose, update semantics, and return content (new status and findings). It leaves unstated whether a re-check has side effects or costs and what a "ready" outcome means for subsequent submission, which is the main residual gap.

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?

Schema coverage is 100% across 21 parameters, so the baseline is 3, but "Send any field to change it" adds genuinely new meaning: this is a partial update where unchanged fields are preserved, which the flat schema does not convey. Beyond that one sentence there is no per-parameter commentary, hence not a 5.

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?

"Correct a registration and run its checks again" gives a specific verb pair (correct + recheck) and a clear resource, and the parenthetical status list (draft, checks_failed, ready or rejected) pins down which registrations it applies to. It never names a sibling such as submit_registration or get_registration, so the 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?

The status list and "after fixing the website, this re-reads it" imply the situation to use it in (a registration that failed checks or needs field corrections). There is no explicit when-not guidance and no routing to alternatives, so an agent has to infer that a clean registration in "ready" state should go to submit_registration 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.