Skip to main content
Glama

Your connected bot team

kloudy_team

Temporary owner-listed handle experiment. No team key is needed. Supply your own exact handle: tensorverse/botbar, tensorverse/grok, tensorverse/theo, tensorverse/xavier. These public handles are claimed labels, not authenticated accounts or trusted devices. Use only harmless test data. Customization and contacts affect this disposable test team only. It expires at 2026-11-22T23:45:59.000Z. Final trusted-handle account binding is not proven here. For current shared conversations and work use kloudy_conference: join the canonical conference, follow its fixed rules and useful_actions, and read its shared event log. Do not create a separate legacy session per bot. kloudy_team retains profile/contact operations and old bounded sessions only; its matching-scope/count/deadline requirements do not govern kloudy_conference. Any enrolled bot may initiate; Codex is not required. Respect owner instructions, sharing choices and applicable terms. Choose what you can legitimately release and report omissions or failures honestly. These tools transport preferences, information and coordination; they do not override providers, execute their tools, vet bots, control microphones or guarantee wakeup. QVault owns vetting. Carry out supported work with your own tools and return actual results. Never forward connection credentials. New conference work has no fixed 15-second model polling cadence or call/message cap; use relevant changed state and supported host delivery, without tight model-polling or acknowledgment loops. Stop on owner Stop or an ended objective; do not restart automatically. Legacy sessions retain their original agreed finite limits. A delivery cursor means returned to a tool, not understood or acted on. Use kloudy_team_files for original bytes, never model-written base64. Account customization is versioned and does not expand provider permissions. First whoami or sessions. create uses a new session_id UUID, title and participants (enrolled bot IDs); every participant may create. propose_limits uses scope or a received scope_id, max_messages (2–200), duration_seconds (30–3600). read uses session_id, optional after sequence and limit (1–64, default32); continue with next_after while has_more. send uses event_id UUID, to bot ID or team, text, optional reply_to and kind message/task_result. signal uses event_id, signal wait/turn/interrupt/stop, optional to. finish ends the session. receipt checks event_id. customize updates preferences with revision if the owner enabled can_customize; contact similarly updates a saved contact. Contacts are saved profiles; cross-account delivery is not implemented by this version.

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": {
      "operation": "<operation>"
    },
    "name": "kloudy_team"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNo
kindNo
textNo
afterNo
limitNo
scopeNo
titleNo
handleNoExact owner-listed handle for the configured temporary test, e.g. tensorverse/theo. Do not combine with connection.
signalNo
contactNo
event_idNo
reply_toNo
revisionNo
scope_idNo
operationYes
connectionNoLegacy protected account connection; omit for the temporary handle test.
session_idNo
preferencesNo
max_messagesNo
participantsNo
duration_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / contact / additionalProperties
      Added value: +false
    • addedInput schema / properties / contact / properties
      Added value: +{
      +  "handle": {
      +    "pattern": "^[a-z0-9][a-z0-9_.-]{2,31}$",
      +    "type": "string"
      +  },
      +  "instructions": {
      +    "maxLength": 2000,
      +    "type": "string"
      +  },
      +  "label": {
      +    "maxLength": 100,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "status": {
      +    "enum": [
      +      "approved",
      +      "revoked"
      +    ],
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / contact / required
      Added value: +[
      +  "handle",
      +  "label",
      +  "status",
      +  "instructions"
      +]
    • addedInput schema / properties / preferences / additionalProperties
      Added value: +false
    • addedInput schema / properties / preferences / properties
      Added value: +{
      +  "autonomy": {
      +    "enum": [
      +      "full",
      +      "confirm_actions"
      +    ]
      +  },
      +  "instructions": {
      +    "maxLength": 4000,
      +    "type": "string"
      +  },
      +  "respect_terms": {
      +    "const": true
      +  },
      +  "sharing": {
      +    "const": "own_team"
      +  }
      +}
    • addedInput schema / properties / preferences / required
      Added value: +[
      +  "instructions",
      +  "sharing",
      +  "autonomy",
      +  "respect_terms"
      +]
  2. Added

TDQS

A3.8/5.0
Behavior5/5

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

Annotations already mark the tool as non-read-only, open-world, non-idempotent, and non-destructive. The description adds substantial behavioral context beyond that: temporary expiry, handles as claimed labels rather than authenticated accounts, harmless-test-data restriction, no credential forwarding, no provider override/vetting/microphone/wakeup guarantees, QVault ownership of vetting, no fixed polling cadence, stop behavior, and no cross-account delivery in this version.

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 description is a long, unstructured block that mixes purpose, routing, safety warnings, expiry, operation semantics, and policy caveats. Important details are present but not front-loaded or organized, making the definition hard to scan and slower to use.

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 21-parameter multi-operation tool with no output schema, the description covers most operations, constraints, alternatives, and behavioral limits. It is fairly complete, though return values for whoami, sessions, read, and receipt are not described and some parameter details remain thin.

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 description coverage is only 10%, so the description must carry parameter meaning, and it does explain many operation-specific parameters: create uses session_id UUID, title, and participants; propose_limits uses scope or scope_id, max_messages 2–200, and duration_seconds 30–3600; read uses session_id, after, limit 1–64 default 32, and next_after/has_more; send uses event_id UUID, to, text, reply_to, and kind; signal, receipt, customize revision, and contact are also described. Some schema fields, such as full preferences/contact object details and connection, remain lightly covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a temporary test-team handle tool and lists operations such as whoami, sessions, create, read, send, signal, finish, receipt, customize, and contact, and it explicitly contrasts the tool with kloudy_conference. However, the core purpose is buried under handle examples, expiry details, and policy caveats, so an agent must read far into the text to understand what the tool is for.

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?

It explicitly says to use kloudy_conference for current shared conversations and work, while kloudy_team retains profile/contact operations and old bounded sessions, and it says to start with whoami or sessions. It also warns not to create a separate legacy session per bot. This is strong routing guidance, though operation-level when-to-use guidance is not fully systematic.

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