Skip to main content
Glama

Copy an interview

duplicate_interview
Destructive

[Positions] Copy a stand-alone interview (not a position's step) as a new draft, optionally renamed or into another company you manage. Results are not copied. Into another company the avatar must be shared with it.

Every argument in full, with examples: get_tool_reference.

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_id": "<interview_id>"
    },
    "name": "duplicate_interview"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoName of the copy. Default: the name with " (copy)".
llm_modelNoYour model id, e.g. "claude-opus-4-8"; "unknown" if unsure. For analytics.
interview_idYesThe stand-alone interview, persona or coaching session to copy (an interview `id` from list_interviews).
conversation_idNoThe conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.
target_merchant_idNoCopy into another company you manage (admins and sub-merchant operators only; other callers always copy into their own company). Default: the interview's company.

Output Schema

NameRequiredDescriptionDefault
interview_idYes
_mcp_instructionsNoServer-issued metadata for this conversation.
source_interview_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / interview_id / description
      Previous value: -"The stand-alone interview, persona or coaching session to copy (interview_def_set.id)."New value: +"The stand-alone interview, persona or coaching session to copy (an interview `id` from list_interviews)."
  2. Changed5 schema fields changed
    • changedInput schema / properties / interview_id / description
      Previous value: -"The stand-alone interview, persona or coaching session to copy (interview_def_set.id). The AI interview of a position step is copied with duplicate_position."New value: +"The stand-alone interview, persona or coaching session to copy (interview_def_set.id)."
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "Your model id, e.g. \"claude-opus-4-8\"; \"unknown\" if unsure. For analytics.",
      +  "type": "string"
      +}
    • changedInput schema / properties / target_merchant_id / description
      Previous value: -"Copy into another company you manage (admins and sub-merchant operators only; other callers always copy into their own company). Another company needs a shared avatar. Default: the interview's company."New value: +"Copy into another company you manage (admins and sub-merchant operators only; other callers always copy into their own company). Default: the interview's company."
    • removedOutput schema / properties / interview_id / description
      Removed value: -"The copy (interview_def_set.id), a draft."
    • removedOutput schema / properties / source_interview_id / description
      Removed value: -"The interview copied (interview_def_set.id)."
  3. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare a mutating, non-idempotent, destructive, open-world operation; the description adds genuinely new facts: the output is a new draft, interview results are not carried over, and cross-company copies require the avatar to be shared. It doesn't explain why the operation is flagged destructive or what the caller must be authorized for beyond 'company you manage'.

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?

Three tight sentences, front-loaded with the core copy semantics and the key exclusion. The trailing pointer to get_tool_reference and the bracketed '[Positions]' prefix add noise but are brief.

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?

An output schema exists, so return values need no explanation, and the description covers scope, result-copying behavior, and the cross-company precondition. Remaining gaps are minor: resulting draft state, quota effects, and explicit caller-permission detail are left to the schema.

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%, so the baseline is 3; every parameter including interview_id, name, target_merchant_id and the analytics fields is already documented in-schema. The description's 'optionally renamed or into another company' largely restates the schema, with only the avatar-sharing precondition adding meaning beyond it.

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?

States a specific verb and resource ('Copy a stand-alone interview ... as a new draft') and explicitly excludes the sibling case ('not a position's step'), which routes the agent away from duplicate_position. The optional rename and cross-company variants are named up front.

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?

The parenthetical 'not a position's step' tells the agent the boundary versus duplicating a position, and 'another company you manage' sketches the eligible-caller condition. It never names the alternative tool outright and gives no guidance on when duplication is preferable to creating fresh via create_interview.

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.