Skip to main content
Glama

Manage the interview assistant

manage_assistant
Destructive

Change the interview assistant's settings, the member's own prompt and the context it reads, keep a call's transcript, file the current call under an interview, remove a paired device, and delete, file or unfile call recordings. Actions: update_settings, remove_device, delete_recording, file_recording, unfile_recording, save_recording, link_call. 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_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: -[
      -  "update_settings",
      -  "remove_device",
      -  "delete_recording",
      -  "file_recording",
      -  "unfile_recording",
      -  "help"
      -]New value: +[
      +  "update_settings",
      +  "remove_device",
      +  "delete_recording",
      +  "file_recording",
      +  "unfile_recording",
      +  "save_recording",
      +  "link_call",
      +  "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 destructiveHint=true and readOnlyHint=false for the whole tool; the description adds value by making clear which actions are destructive (delete_recording, remove_device) versus benign (save_recording, unfile_recording). It does not state irreversibility, required permissions, or whether delete_recording is permanent, so it stays at adequate rather than strong.

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?

Capability prose is front-loaded in a single dense sentence, then the action list, then the discovery hint — no filler. The action list does restate the schema enum verbatim, but it usefully exposes the action names next to the prose descriptions, so the redundancy earns most of its place.

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 seven-action tool with a nested, unconstrained params object and no output schema, the definition leans entirely on the 'help' action to supply field details, forcing an extra round trip before any real invocation. It never indicates what the actions return or which require 'key' versus 'params'. The self-documenting pattern is legitimate but leaves the agent short of what it needs for a destructive multi-action tool.

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%, so baseline is 3. The description's only parameter-level contribution is the 'help' escape hatch for discovering each action's fields, which is genuinely useful given that 'params' is an open object with additionalProperties=true and no documented shape. It adds no semantics for 'key' or for how params differ per action, deferring all of that to a runtime call.

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 concrete verbs and resources (change settings, keep a transcript, file a call under an interview, remove a paired device, delete/file/unfile recordings) and maps them onto the action enum, so the agent knows the tool's scope. It does not distinguish itself from overlapping siblings such as update_settings or get_assistant, which is the only thing keeping it below a 5.

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 only implied through the enumerated operations: an agent can infer that 'file the current call under an interview' applies when a call is in progress, and that delete/remove actions apply to existing artifacts. There is no explicit when-to-use/when-not guidance and no routing away from sibling tools like update_settings or manage_interviews that may cover adjacent territory. The 'help' instruction is procedural rather than selection guidance.

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.