Skip to main content
Glama
Sign In

Fyreflock

by io.github.FuloxDev
OverviewDiscussionsAdmin

Leave or skip from the chat box

fyreflock_app_leave
Destructive

Ends the conversation, or the search, from the chat box. The box's version of fyreflock_leave and fyreflock_next in one: a model relaying for the person uses those. Called only by the box with its box_key. The other person is told it ended; with next it joins the queue again at once, otherwise the box goes idle. With nothing open and no search it changes nothing. Returns the whole box state, the same shape fyreflock_app_wait gives, with ended set to leave or next.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "fyreflock_app_leave"
  }
}

Input Schema

NameRequiredDescriptionDefault
nextNoAlso look for somebody else straight away, as fyreflock_next does.
box_keyNoThe key the chat box received in fyreflock_open's result _meta. Only the box holds one, so only the box can call this tool.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / box_key / description
      Previous value: -"Set by the chat box itself."New value: +"The key the chat box received in fyreflock_open's result _meta. Only the box holds one, so only the box can call this tool."
    • addedInput schema / properties / next / description
      Added value: +"Also look for somebody else straight away, as fyreflock_next does."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the destructiveHint=true annotation, the description discloses the externally visible consequence (the other person is told it ended), the state transition for each branch (requeue vs idle), and the no-op case when nothing is open and no search is running. That is exactly the context the annotation cannot convey.

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 core action and caller restriction are front-loaded and every sentence carries information about state or return value. It is dense and slightly run-on, but no sentence is filler.

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?

With no output schema, the description compensates by describing the return value as the full box state matching fyreflock_app_wait's shape, with ended set to leave or next. Caller restrictions, side effects, and return shape are all covered for a two-parameter tool.

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 both parameters are already documented, but the description still adds behavioral meaning: next means immediate requeue rather than idle, and box_key is scoped to the box alone because only it holds one. Modest value added over an already-complete schema.

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?

"Ends the conversation, or the search, from the chat box" gives a specific verb and resource, and the following sentence explicitly positions it as the box-side counterpart to fyreflock_leave and fyreflock_next, which are named as the model-relay variants. An agent can distinguish this from the two similarly named siblings without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states both the caller restriction ("Called only by the box with its box_key") and the alternative route (a model relaying for the person uses fyreflock_leave / fyreflock_next). The next=true case is also given a condition: it rejoins the queue at once rather than going idle.

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

All Fyreflock 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