Skip to main content
Glama

Read the interview assistant

get_assistant
Read-onlyIdempotent

The interview assistant: its settings with the member's own prompt and context, its answer to a question, the call it is on, paired devices and call recordings. Actions: settings, devices, recordings, recording, ask, current_call, setup_link. 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": "get_assistant"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoThe item's key as the matching list answered it.
actionYes
paramsNoFields for the action. Call with action "help" to list each action's fields.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "settings",
      -  "devices",
      -  "recordings",
      -  "recording",
      -  "help"
      -]New value: +[
      +  "settings",
      +  "devices",
      +  "recordings",
      +  "recording",
      +  "ask",
      +  "current_call",
      +  "setup_link",
      +  "help"
      +]
  2. Added

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine non-annotation context: this is a single polymorphic tool dispatched by an action field, and a self-describing "help" action exists. It omits anything about the shape of a successful response (no output schema) or what setup_link produces, so it adds some value but not rich behavioral detail.

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?

Wirklich compact: one telegraphic sentence naming the resource and its readable facets, one listing actions, one pointing to help. Front-loaded with the resource and zero filler. The fragment style is slightly elliptical but nothing is redundant.

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 an eight-action polymorphic tool with a free-form nested params object and no output schema, the definition does the minimum a caller needs: it names the actions and routes the agent to help for field details. It leaves the agent without any advance knowledge of per-action parameters or return shapes, which for a multi-action dispatcher is a meaningful gap relative to the tool's 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 67%: the key and params fields carry their own descriptions and action has an enum. The description adds one real semantic — that per-action field lists are discoverable via action "help" — which meaningfully explains the free-form nested params object. It does not, however, document any individual action's required fields or state whether key applies to some actions but not others.

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 names the resource (the interview assistant) and enumerates exactly what is readable from it — settings with the member's prompt and context, an answer to a question, the current call, paired devices, and recordings — then lists the seven actions. That is far more specific than the title alone and lets an agent map intent to action. It does not, however, contrast itself with the manage_assistant sibling, which is the most likely confusion point.

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?

Usage is implied by the subjective framing (settings/answers/devices/recordings are read via this tool) and the agent is told to call action "help" to enumerate fields. There is no explicit when-to-use versus manage_assistant for mutations, nor any statement of when this tool is the wrong choice. Procedural guidance for discovery exists, but selection guidance does not.

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.