Skip to main content
Glama
Sign In

Oyeh

by com.amkentech.channel
OverviewDiscussionsAdmin

Leave a group

leave_group
Destructive

Leave a group, when your person asks. If your person OWNS the group, leaving ends it for everyone: every member is told it ended and notes nobody read yet are taken back. Ownership can't be handed over. For the owner the first call only explains that; call again with confirm true once your person says to go ahead.

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": {
      "group": "<group>"
    },
    "name": "leave_group"
  }
}

Input Schema

NameRequiredDescriptionDefault
groupYesThe group's id or exact name, from my_groups
confirmNoOwner only: true once your person agreed that leaving ends the group

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the destructiveHint=true annotation by disclosing exactly what is destroyed (the group ends for every member), the side effects (all members notified, unread notes taken back), and a hard constraint (ownership can't be handed over). The deliberate two-phase confirm behavior is behavior an agent could not infer from the schema.

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?

The purpose is front-loaded in four words, followed by escalating consequence detail and finally the call protocol. Dense but nearly every clause carries operational value; the ownership sentence is slightly compressed but not wasteful.

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

Completeness5/5

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

For a destructive, non-idempotent, no-output-schema tool with two params, the description covers consequences, side effects, irreversibility, and the confirm protocol. An agent has everything needed to act correctly without further probing.

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 100%, so baseline is 3, but the description adds real meaning: it explains that confirm is owner-only and that a first call without it is non-mutating and informational. That reframes the parameter from a bare boolean into a two-step safeguard.

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?

Names a specific verb and resource ("Leave a group") and immediately scopes it with the condition "when your person asks." It clearly distinguishes leaving-as-member from leaving-as-owner, though it never names the sibling end_group, which likely overlaps with the owner path.

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 an explicit trigger ("when your person asks") and a precise two-step invocation protocol for the owner case: first call only explains, second call with confirm true proceeds. Missing is any routing advice toward end_group or other sibling alternatives, which is the main gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Oyeh toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources