Skip to main content
Glama

Manage interviews

manage_interviews
Destructive

Create and update interviews and rounds, notes, transcripts, briefings, recordings, scorecards, debriefs, invites, checks, thank-you notes and next-steps or feedback notes to employers. Actions: create, update, add_round, update_round, add_correspondence, add_transcript, link_calendar, generate_briefing, attach_recording, detach_recording, score_round, add_interviewer, save_debrief, mark_invite_seen, rate_tracking, answer_check, mark_thank_you_done, draft_thank_you, draft_follow_up. Call with action "help" for each action's fields.

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": {
      "action": "<action>"
    },
    "name": "manage_interviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
paramsNoFields for the action. Call with action "help" to list each action's fields.
check_idNoAn interview check-in's id from get_interviews follow_ups (checks[].id).
event_idNoAn interview round's id (a process's interviews[].id) from get_interviews list.
invite_idNoAn interview invite's id from get_interviews follow_ups (invites[].id).
interview_idNoAn interview's id from get_interviews list, or a follow_ups item's processId.
follow_up_keyNoA thank-you follow-up's key from get_interviews follow_ups (followUps[].key).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / event_id / description
      Previous value: -"An interview round's id from get_interviews get."New value: +"An interview round's id (a process's interviews[].id) from get_interviews list."
  2. Changed3 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "create",
      -  "update",
      -  "add_round",
      -  "update_round",
      -  "add_correspondence",
      -  "add_transcript",
      -  "link_calendar",
      -  "generate_briefing",
      -  "attach_recording",
      -  "detach_recording",
      -  "score_round",
      -  "add_interviewer",
      -  "save_debrief",
      -  "act_on_suggestion",
      -  "confirm_invite",
      -  "answer_check",
      -  "mark_thank_you_done",
      -  "draft_thank_you",
      -  "help"
      -]New value: +[
      +  "create",
      +  "update",
      +  "add_round",
      +  "update_round",
      +  "add_correspondence",
      +  "add_transcript",
      +  "link_calendar",
      +  "generate_briefing",
      +  "attach_recording",
      +  "detach_recording",
      +  "score_round",
      +  "add_interviewer",
      +  "save_debrief",
      +  "mark_invite_seen",
      +  "rate_tracking",
      +  "answer_check",
      +  "mark_thank_you_done",
      +  "draft_thank_you",
      +  "draft_follow_up",
      +  "help"
      +]
    • changedInput schema / properties / interview_id / description
      Previous value: -"An interview's id from get_interviews list."New value: +"An interview's id from get_interviews list, or a follow_ups item's processId."
    • removedInput schema / properties / suggestion_id
      Removed value: -{
      -  "description": "A suggestion's id from get_interviews get.",
      -  "pattern": "^[a-f0-9]{32}$",
      -  "type": "string"
      -}
  3. Added

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered structurally. The description adds real value by exposing the action surface (attach/detach_recording, mark_invite_seen, save_debrief) and the `help` self-description mechanism, letting an agent see what kinds of mutation exist. It does not, however, flag which of the nineteen actions are the destructive or irreversible ones, nor any permission requirements — a notable omission given destructiveHint=true.

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

Conciseness2/5

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

The first sentence is a run-on padding list ("notes, transcripts, briefings, recordings, scorecards, debriefs, invites, checks, thank-you notes and next-steps or feedback notes"), and the action list duplicates the enum verbatim, consuming most of the text for zero marginal information. Only the trailing `help` sentence carries unique value, and it is buried at the end rather than front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive 20-action dispatcher with a nested opaque `params` object and no output schema, the description is thin but not absent: it scopes the domain and provides an escape hatch via `action: "help"`. It never explains how actions map to the different ID parameters or what a successful result contains, leaving real gaps for a tool of this complexity.

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 high (86%) and the top-level ID fields carry their own provenance descriptions, so the baseline is 3. The critical gap is the free-form `params` bag (additionalProperties: true), whose per-action fields appear nowhere in the schema; the description only redirects to `action: "help"` rather than explaining the relationship between the top-level `check_id`/`event_id`/`invite_id`/`interview_id` and specific actions.

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?

The description opens with a concrete verb pair ("Create and update") and an enumerated resource list (interviews, rounds, notes, transcripts, scorecards, debriefs, invites, checks), then names all nineteen action values plus help. This makes the mutation scope legible at a glance. It loses a point because it never distinguishes itself from the obvious sibling `get_interviews` (the read counterpart), so an agent must infer the read/write split from the verb alone.

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 only actionable routing guidance is "Call with action 'help' for each action's fields," which is genuinely useful for a 20-way dispatcher but is about discovery, not selection. There is no statement of when to pick this over `get_interviews`, no prerequisites, and no indication of which action suits which situation.

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.