Skip to main content
Glama
CRAFT Content MCP Server

CRAFT Content MCP Server

Case Study Generator

case_study_generator
Read-only

Build a customer case study from your challenge, solution, and results, or generate interview questions to collect them. Produces a headline, story, customer quote, social and email copy.

Instructions

Helps you decide how to present a customer result as a case study, built from the customer name, your product and the challenge, solution and results you give (mode full), or an interview kit to collect them (mode discovery). Optional customer industry, quote, interview notes and business model fit the wording to the customer. Returns a headline, the story with each result you list, a customer quote, social and email copy, and sector notes when the sector can be read from your text. A bracket marks anything you did not give. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of testimonial_capture when you need a full challenge, solution and results story. Ask whether written customer approval covers the exact material and intended use.

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": {
      "customer_name": "<customer_name>",
      "your_product": "<your_product>"
    },
    "name": "case_study_generator"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNofull builds the case study and needs the challenge, solution and results; discovery returns interview questions for collecting them. Format is text using one of the listed labels. For example, "full".
resultsNoMeasurable outcomes, one per line or per semicolon (needed in full mode). Format is text. For example, "Company-reported pilot reduced approval time from 12 to 9 days in October 2026.".
solutionNoHow your product solved it (needed in full mode). Format is text. For example, "invoice review service".
challengeNoThe customer's challenge or problem (needed in full mode). Format is text. For example, "invoice exceptions delay month-end close".
your_sectorNoOptional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. Format is text using one of the listed labels. For example, "logistics_tech".
your_productYesYour product or service name. Format is text. For example, "invoice review service".
customer_nameYesCustomer or company name. Format is text. For example, "an approved anonymous manufacturer".
business_modelNoOptional: how you charge, so the advice fits it. If omitted, it is read from your text and the answer says how. Format is text using one of the listed labels. For example, "saas".
customer_quoteNoOptional: a direct quote from the customer. Format is text. For example, "Company-reported pilot reduced approval time from 12 to 9 days in October 2026.".
interview_notesNoOptional: raw interview notes or a transcript. In full mode they fill a missing challenge, solution or results; the answer says they were not used when you gave all three. Format is text. For example, "Finance lead reports invoice delays and plans a pilot.".
customer_industryNoThe customer's industry, used for context. Format is text. For example, "manufacturing".
publication_approvalNoOptional confirmed written approval for this exact customer name, figures, quote and intended use. Ask before publication. A draft cannot grant customer permission. Format is text using one of the listed labels. For example, "approved".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changedv2.2.25
    • addedInput schema / properties / business_model
      Added value: +{
      +  "description": "Optional: how you charge, so the advice fits it. If omitted, it is read from your text and the answer says how. Format is text using one of the listed labels. For example, \"saas\".",
      +  "enum": [
      +    "saas",
      +    "services",
      +    "connectivity",
      +    "transactions",
      +    "marketplace",
      +    "hardware_software",
      +    "investment"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / challenge / description
      Previous value: -"Business challenge faced"New value: +"The customer's challenge or problem (needed in full mode). Format is text. For example, \"invoice exceptions delay month-end close\"."
    • changedInput schema / properties / customer_industry / description
      Previous value: -"Customer's industry"New value: +"The customer's industry, used for context. Format is text. For example, \"manufacturing\"."
    • changedInput schema / properties / customer_name / description
      Previous value: -"Customer company name"New value: +"Customer or company name. Format is text. For example, \"an approved anonymous manufacturer\"."
    • addedInput schema / properties / customer_quote
      Added value: +{
      +  "description": "Optional: a direct quote from the customer. Format is text. For example, \"Company-reported pilot reduced approval time from 12 to 9 days in October 2026.\".",
      +  "type": "string"
      +}
    • removedInput schema / properties / customer_size
      Removed value: -{
      -  "description": "Company size",
      -  "type": "string"
      -}
    • addedInput schema / properties / interview_notes
      Added value: +{
      +  "description": "Optional: raw interview notes or a transcript. In full mode they fill a missing challenge, solution or results; the answer says they were not used when you gave all three. Format is text. For example, \"Finance lead reports invoice delays and plans a pilot.\".",
      +  "type": "string"
      +}
    • addedInput schema / properties / mode
      Added value: +{
      +  "description": "full builds the case study and needs the challenge, solution and results; discovery returns interview questions for collecting them. Format is text using one of the listed labels. For example, \"full\".",
      +  "enum": [
      +    "full",
      +    "discovery"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / publication_approval
      Added value: +{
      +  "description": "Optional confirmed written approval for this exact customer name, figures, quote and intended use. Ask before publication. A draft cannot grant customer permission. Format is text using one of the listed labels. For example, \"approved\".",
      +  "enum": [
      +    "approved",
      +    "not_approved",
      +    "unknown"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / quote
      Removed value: -{
      -  "description": "Customer quote",
      -  "type": "string"
      -}
    • changedInput schema / properties / results / description
      Previous value: -"Quantified outcomes"New value: +"Measurable outcomes, one per line or per semicolon (needed in full mode). Format is text. For example, \"Company-reported pilot reduced approval time from 12 to 9 days in October 2026.\"."
    • changedInput schema / properties / solution / description
      Previous value: -"How your product solved it"New value: +"How your product solved it (needed in full mode). Format is text. For example, \"invoice review service\"."
    • changedInput schema / properties / your_product / description
      Previous value: -"Your product name"New value: +"Your product or service name. Format is text. For example, \"invoice review service\"."
    • addedInput schema / properties / your_sector
      Added value: +{
      +  "description": "Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. Format is text using one of the listed labels. For example, \"logistics_tech\".",
      +  "enum": [
      +    "logistics_tech",
      +    "fintech",
      +    "saas",
      +    "vertical_saas",
      +    "ai_native",
      +    "ites",
      +    "telecom",
      +    "software",
      +    "cybersecurity",
      +    "other"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "customer_name",
      -  "challenge",
      -  "solution",
      -  "results",
      -  "your_product"
      -]New value: +[
      +  "customer_name",
      +  "your_product"
      +]
  2. First observedv1.0.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint/destructiveHint annotations, it discloses operational traits an agent could not infer: no sign-in required, no storage of inputs or outputs, hosted usage metadata is recorded, and the bracket convention marking anything the caller did not supply. It also specifies error behavior — missing required fields or invalid values return an error naming what to supply or correct.

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 opening sentence front-loads what the tool does and the two modes, and nearly every clause carries distinct information (inputs, optional enrichments, outputs, privacy, error handling, sibling routing). It is a single dense paragraph of roughly 150 words, which borders on run-on and could be split into bullets for faster scanning.

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?

With 12 parameters, four enums, and no output schema, the description does the work that would otherwise be missing: it summarizes the return payload, explains the bracket convention for omitted inputs, describes the privacy/auth posture, and covers failure modes. An agent has everything needed to choose a mode and call it correctly.

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%, so the schema already documents all 12 parameters in detail and the baseline would be 3. The description still adds cross-parameter meaning: challenge/solution/results are only needed in full mode, and interview_notes will backfill a missing challenge/solution/results but the answer states they were unused when all three were supplied — a conditional behavior not visible in the schema.

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 names a specific verb and artifact — turning a customer result into a case study — and enumerates exactly what it produces (headline, story with each result, quote, social and email copy, sector notes). It also distinguishes the two modes (full vs discovery interview kit) and explicitly sets itself apart from the sibling testimonial_capture.

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 an explicit routing rule: 'Use this instead of testimonial_capture when you need a full challenge, solution and results story.' It also states which mode to pick depending on whether you already have the challenge/solution/results or need to collect them, and adds a precondition about written customer approval.

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