Skip to main content
Glama

Customer Interview Kit

customer_interview_kit
Read-only

Generate a tailored customer interview guide and synthesis templates from your interview type, product context, and target persona, so you know exactly what to ask before conducting research interviews.

Instructions

Helps you decide what to ask customers to test your hunch: it takes the interview type, the product context and the person you are interviewing, and returns an interview guide that fits the interview type, the sector and the product complexity. Questions use the sector's own language (the sector is chosen, or read from your inputs), your hypotheses are kept whole, and synthesis templates are included. 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 icp_interview_synthesizer when you need questions and synthesis templates before conducting interviews.

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": {
      "interview_type": "<interview_type>",
      "product_context": "<product_context>",
      "target_persona": "<target_persona>"
    },
    "name": "customer_interview_kit"
  }
}

Input Schema

NameRequiredDescriptionDefault
industryNoIndustry affects terminology and context. Leave it out and the sector is read from your other inputs. Format is text using one of the listed labels. For example, "saas".
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".
business_modelNoOptional: how you earn revenue, so the advice fits it (saas, services, connectivity, transactions, marketplace, hardware_software or investment). Leave it out and the tool reads it from your other inputs and says how it read it. Format is text using one of the listed labels. For example, "saas".
interview_typeYesType of interview determines question focus. Format is text using one of the listed labels. For example, "discovery".
key_hypothesesNoOptional: Hypotheses to validate during interview, one per line or separated by semicolons. Format is text. For example, "confirm who approves invoice exceptions".
target_personaYesWho you're interviewing (role/title). Format is text. For example, "finance director".
product_contextYesProduct/service being researched. Format is text. For example, "checks invoice exceptions before approval".
product_complexityNoAffects technical depth of questions. Format is text using one of the listed labels. For example, "simple".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changedv2.2.25
    • addedInput schema / properties / business_model
      Added value: +{
      +  "description": "Optional: how you earn revenue, so the advice fits it (saas, services, connectivity, transactions, marketplace, hardware_software or investment). Leave it out and the tool reads it from your other inputs and says how it read it. Format is text using one of the listed labels. For example, \"saas\".",
      +  "enum": [
      +    "saas",
      +    "services",
      +    "connectivity",
      +    "transactions",
      +    "marketplace",
      +    "hardware_software",
      +    "investment"
      +  ],
      +  "type": "string"
      +}
    • removedInput schema / properties / customer_segment
      Removed value: -{
      -  "description": "Specific persona/segment to interview",
      -  "type": "string"
      -}
    • removedInput schema / properties / duration
      Removed value: -{
      -  "description": "Target interview length",
      -  "type": "string"
      -}
    • addedInput schema / properties / industry
      Added value: +{
      +  "description": "Industry affects terminology and context. Leave it out and the sector is read from your other inputs. Format is text using one of the listed labels. For example, \"saas\".",
      +  "enum": [
      +    "saas",
      +    "fintech",
      +    "logistics_tech",
      +    "vertical_saas",
      +    "ai_native",
      +    "ites",
      +    "telecom",
      +    "software",
      +    "cybersecurity",
      +    "ecommerce",
      +    "marketplace",
      +    "enterprise_software",
      +    "consumer",
      +    "other"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / interview_type / description
      Previous value: -"Type: discovery, validation, feedback, churn"New value: +"Type of interview determines question focus. Format is text using one of the listed labels. For example, \"discovery\"."
    • addedInput schema / properties / interview_type / enum
      Added value: +[
      +  "discovery",
      +  "validation",
      +  "feedback",
      +  "churn",
      +  "win_loss",
      +  "persona_research"
      +]
    • addedInput schema / properties / key_hypotheses
      Added value: +{
      +  "description": "Optional: Hypotheses to validate during interview, one per line or separated by semicolons. Format is text. For example, \"confirm who approves invoice exceptions\".",
      +  "type": "string"
      +}
    • removedInput schema / properties / key_questions
      Removed value: -{
      -  "description": "Primary research questions (2-3)",
      -  "type": "string"
      -}
    • addedInput schema / properties / product_complexity
      Added value: +{
      +  "description": "Affects technical depth of questions. Format is text using one of the listed labels. For example, \"simple\".",
      +  "enum": [
      +    "simple",
      +    "moderate",
      +    "complex",
      +    "highly_technical"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / product_context
      Added value: +{
      +  "description": "Product/service being researched. Format is text. For example, \"checks invoice exceptions before approval\".",
      +  "type": "string"
      +}
    • removedInput schema / properties / research_objective
      Removed value: -{
      -  "description": "What you're trying to learn",
      -  "type": "string"
      -}
    • addedInput schema / properties / target_persona
      Added value: +{
      +  "description": "Who you're interviewing (role/title). Format is text. For example, \"finance director\".",
      +  "type": "string"
      +}
    • 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: -[
      -  "research_objective",
      -  "interview_type",
      -  "customer_segment"
      -]New value: +[
      +  "interview_type",
      +  "product_context",
      +  "target_persona"
      +]
  2. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint=false and destructiveHint=false, yet the description still adds real context: no sign-in, no storage of inputs or outputs, hosted usage metadata recorded, and a clear error contract naming what to supply or correct. It stops short of describing the guide's structure or length, but the safety and privacy profile is unusually well covered.

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 core purpose is front-loaded in the first clause, and the subsequent sentences each carry a distinct payload (terminology adaptation, hypothesis preservation, privacy, error behavior, routing). It runs long without paragraph breaks, but almost no sentence is expendable.

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 an 8-parameter generator with no output schema, the description covers what is produced (questions plus synthesis templates), how it is shaped (sector language, complexity, interview type), and the operational constraints (read-only, no persistence, error behavior). An agent has enough to call it correctly without further probing.

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?

Schema coverage is 100% and the schema descriptions already explain the enum labels, optionality and the sector-inference fallback. The description echoes those points ('the sector is chosen, or read from your inputs', 'your hypotheses are kept whole') but adds no format or interaction detail the schema lacks. Baseline 3 is appropriate when the schema does the heavy lifting.

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 verb and artifact: it takes interview_type, product_context and target_persona and returns an interview guide tailored to interview type, sector and product complexity. It names the sibling it replaces (icp_interview_synthesizer), so an agent can distinguish it without opening another 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?

Gives an explicit routing rule: 'Use this instead of icp_interview_synthesizer when you need questions and synthesis templates before conducting interviews.' The alternative and the selecting condition are both stated, plus the timing (before conducting interviews).

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