Skip to main content
Glama
CRAFT Content MCP Server

CRAFT Content MCP Server

Turn this customer result into content

customer_result_to_content
Read-only

Converts a verified customer result sentence into a proof card, case study draft, post, or newsletter section while preserving exact wording and checking approval gaps.

Instructions

Helps you decide how to turn a customer result into a case study, a post and a newsletter while preserving its exact sentence. Needs the exact result sentence with its qualifier and source label, source and date, your role, approval, your own view and a reader action. Returns a proof card, first drafts and a sentence check. Optional proof details expose gaps. Written approval is required for your own customer; without it, returns the card and questions only. Chat collects the facts; the results view shows them. No form. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing or invalid brief fields return field-specific errors. Missing written approval for your own customer returns the proof card and questions only. Use this instead of case_study_generator when you need a proof card and several drafts preserving one exact result sentence.

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": {
      "exact_sentence": "<exact_sentence>",
      "source_url": "<source_url>",
      "source_date": "<source_date>",
      "source_kind": "<source_kind>",
      "source_label": "<source_label>",
      "measured_result": "<measured_result>",
      "buyer_role": "<buyer_role>",
      "relationship": "<relationship>",
      "approval": "<approval>",
      "as_of_date": "<as_of_date>",
      "story_published": "<story_published>",
      "customer_name": "<customer_name>",
      "product": "<product>",
      "call_to_action": "<call_to_action>"
    },
    "name": "customer_result_to_content"
  }
}

Input Schema

NameRequiredDescriptionDefault
productYesYour product or vendor name. Format is text. For example, "invoice review service".
approvalYesFormat is a JSON object. For example, {"status":"written","approver":"finance director","date":"2026-11-17","uses":["case study"]}.
headlineNoYour own headline, if available. Format is text. For example, "Reducing invoice approval delays".
solutionNoWhat was done, from the approved story. Format is text. For example, "invoice review service".
challengeNoThe customer problem from the approved story. Format is text. For example, "invoice exceptions delay month-end close".
as_of_dateYesThe date of this run as year, month and day. Supplied by chat so repeats stay identical. Format is text in YYYY-MM-DD form. For example, "2026-11-17".
buyer_roleYesFormat is text using one of the listed labels. For example, "vendor".
buyer_viewNoYour own view in whole sentences. The tool will not invent it. Format is text. For example, "Finance teams need a clear owner for each invoice exception.".
source_urlYesPublic source or approved evidence link, using https. Format is text. For example, "https://example.org/approved-evidence".
source_dateYesPublication or evidence date as year, month and day, or not stated. Keep it separate from the measurement period. Format is text in YYYY-MM-DD form. For example, "2026-10-31".
source_kindYesWho stands behind the result. A company report is not independent evidence. Format is text using one of the listed labels. For example, "company_reported".
relationshipYesFormat is text using one of the listed labels. For example, "own_customer".
source_labelYesThe source label already inside the exact sentence, for example company-reported. Format is text.
customer_nameYesCustomer label, including an approved anonymous description. Format is text. For example, "an approved anonymous manufacturer".
proof_detailsNoFormat is a JSON object. For example, {"qualifier":"in the measured pilot","counted":"120 eligible invoices","definition":"days from invoice receipt to approval"}.
call_to_actionYesOne action you want the reader to take. Format is text. For example, "book a discovery call".
exact_sentenceYesCopy the result exactly, keeping its qualifier and source label inside this sentence. Format is text. For example, "Company-reported pilot reduced approval time from 12 to 9 days in October 2026.".
measured_resultYesFalse for a story with no measured outcome. Never infer an improvement from exposure or scale counts. Format is true or false. For example, true.
published_storyNoThe already published story as plain text. Used as source without rebuilding it. Format is text. For example, "Invoice exceptions delay close. Review unresolved exceptions weekly with finance.".
story_publishedYesFormat is true or false. For example, true.
source_checked_dateNoThe date you reopened the source, as year, month and day. This is not the publication date. Format is text in YYYY-MM-DD form. For example, "2026-11-17".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.2.25

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the readOnlyHint/destructiveHint/openWorldHint annotations, it discloses privacy and hosting behavior (no sign-in, no stored inputs or outputs, hosted usage metadata recorded), the failure mode for invalid brief fields, and the degraded return path when written approval is missing. It does not describe pagination or sizing of drafts, but for a stateless read-only tool this is substantial added context.

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

Conciseness3/5

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

The purpose and return values are front-loaded, but the paragraph is a dense run-on that repeats the missing-approval outcome twice in near-identical wording ("without it, returns the card and questions only" and again near the end). The chat-versus-results-view sentence is tangential to invoking the tool.

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 21-parameter tool with nested objects and no output schema, the description supplies the missing return contract (proof card, drafts, sentence check), the error behavior, the approval gate, and the privacy posture. Nothing an agent needs in order to call it correctly or interpret a degraded response appears to be absent.

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 already 100%, so the baseline is 3, but the description adds meaning the schema does not: the exact sentence must keep its qualifier and source label inside it, approval must be in writing and scoped to uses, and proof_details is optional yet exposes gaps. That clarifies intent rather than merely restating field names.

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 concrete transformation (customer result into case study, post, newsletter) and names the three deliverables returned (proof card, first drafts, sentence check). It explicitly separates itself from case_study_generator by requiring preservation of one exact sentence, so an agent can pick between them without opening either schema.

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

Usage Guidelines5/5

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

It gives a direct routing rule: use this instead of case_study_generator when you need a proof card plus several drafts preserving one exact result sentence. It also states the prerequisite branch — written approval is required for your own customer, otherwise only the card and questions come back — and clarifies that chat collects the facts rather than a form.

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