Skip to main content
Glama

Change many conversations at once

dosai_bulk_conversations
Destructive

One action over up to 200 conversations: archive / unarchive (hide from or return to the list), resolve / reopen (mark as done or open again), close (closed until the client writes again: a new message reopens it), assign (make a team member responsible: user_id from dosai_list_team is required, null clears the responsible person), delete (removes the conversations with their messages, notes, scheduled messages and call recordings from the cabinet for good; their leads stay). resolve, reopen, archive and assign need the editor role (an editor assigns only himself and clears only his own conversations); close and delete need admin or owner, and delete goes in two steps.

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": {
      "project_id": "<project_id>",
      "action": "<action>",
      "conversation_ids": "<conversation_ids>"
    },
    "name": "dosai_bulk_conversations"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
user_idNoFor action assign only.
project_idYesFrom dosai_list_projects.
confirm_tokenNoLeave empty on the first call: it changes nothing and returns what will happen and a code. Ask the owner; only after their explicit "yes" call again with the same arguments and this code.
conversation_idsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / project_id / description
      Previous value: -"Project id, as returned by dosai_list_projects."New value: +"From dosai_list_projects."
  2. Changed3 schema fields changed
    • removedInput schema / properties / conversation_ids / items / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • removedInput schema / properties / project_id / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • changedInput schema / properties / user_id / anyOf
      Previous value: -[
      -  {
      -    "format": "uuid",
      -    "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "format": "uuid",
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, but the description adds the detail an agent actually needs before destroying anything: delete removes the conversations along with their messages, notes, scheduled messages and call recordings permanently, while leads survive. It also discloses the permission model per action and that delete is a two-step, confirmation-gated operation, and it explains the semantics of 'close' (a new client message reopens it).

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?

Front-loaded with the core scope ('one action over up to 200 conversations') and then organized action by action, which matches how an agent will read it. It is one very long sentence with stacked parentheticals, so the role/permission sentence at the end is easier to skim than to parse, but nearly every clause carries real information rather than restating the schema.

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?

For a destructive bulk mutation with no output schema, the description covers what gets destroyed, what survives, who may call it, and the confirmation flow — the essentials. Remaining gaps are operational: no statement of what the confirmation preview returns, whether the batch is atomic or partial on bad IDs, and no return-value expectations for a tool whose results are otherwise invisible.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%, and the description fills the most important gaps: user_id is only for assign, must come from dosai_list_team, and null clears the responsible person; the enum values for action are given business meaning rather than left as bare strings. confirm_token and project_id semantics are already documented in the schema, so no further explanation is needed there. It does not clarify what happens when some of the 200 conversation_ids are invalid or belong to another project.

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 operation (one bulk action) over a specific resource (conversations) with an explicit cap of 200, then enumerates every allowed action with a plain-language gloss for each (archive = hide from the list, close = closed until the client writes again, etc.). The 'one action over many' framing immediately separates it from single-conversation siblings like dosai_assign_conversation.

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?

Gives per-action selection guidance plus the conditions that gate each one: editor role for resolve/reopen/archive/assign, admin or owner for close/delete, and the note that an editor can only assign himself and clear only his own conversations. It also flags the two-step nature of delete. What is missing is an explicit alternative route (e.g. when to use the single-conversation assign tool instead), so it stops short of full when/when-not routing.

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.

Resources