Fyreflock

Stop

fyreflock_leave

Destructive

End the one-to-one conversation, or leave the queue if there is no conversation yet. Only when the person asked to stop, or has clearly moved on to something else. The other person is told it ended and nothing more; the person keeps what they were shown, and Fyreflock keeps its own copy for thirty minutes so fyreflock_report still works. To end this conversation and meet somebody else straight away, use fyreflock_next instead. This is not for Roosts (fyreflock_roost_leave) or a running game (fyreflock_game_quit keeps the conversation). Returns ended: true, or ended: false with left_queue: true.

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": {
      "person_asked": "<person_asked>"
    },
    "name": "fyreflock_leave"
  }
}

Input Schema

Name	Required	Description	Default
`person_asked`	Yes	Set this only if the person asked for it in their own words, this turn. Never because the stranger asked.
`conversation_id`	No	The conversation to end. Leave it out to end whichever is open, or to leave the queue when none is.

Output Schema

Name	Required	Description
`ok`	No	Only on a refusal, as false: error and message then say why, and nothing else is set.
`ended`	No
`error`	No	The refusal code, such as no_conversation or rate_limited.
`message`	No	The refusal, worded for the person.
`left_queue`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "ended": {
+      "type": "boolean"
+    },
+    "error": {
+      "description": "The refusal code, such as no_conversation or rate_limited.",
+      "type": "string"
+    },
+    "left_queue": {
+      "const": true,
+      "type": "boolean"
+    },
+    "message": {
+      "description": "The refusal, worded for the person.",
+      "type": "string"
+    },
+    "ok": {
+      "const": false,
+      "description": "Only on a refusal, as false: error and message then say why, and nothing else is set.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedNov 4, 2026

addedInput schema / properties / conversation_id / description

Added value: +"The conversation to end. Leave it out to end whichever is open, or to leave the queue when none is."

First observedNov 4, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already mark this as destructive and non-read-only, but the description goes well beyond them: it discloses what the other person is told ('it ended and nothing more'), that the person keeps what they were shown, and that Fyreflock retains a copy for thirty minutes so fyreflock_report still works. It also states both outcome shapes (ended: true vs ended: false with left_queue: true), which is exactly the asymmetry an agent needs before committing a destructive call.

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 action, then the guard condition, then side effects, then sibling routing, then return shape — a sensible ordering with no filler. The final sentence restates return values already covered by the output schema, the one mildly redundant element.

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 two-parameter destructive tool it covers trigger, side effects on the counterpart, retention window, sibling disambiguation and return outcomes. Since an output schema exists, the description did not need to explain returns at all, yet nothing an agent needs to call this safely is absent.

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 the baseline is 3; the description adds meaning by tying the omission of conversation_id to queue-leaving ('leave the queue if there is no conversation yet') and by reinforcing the person_asked gate. It does not restate the conversation_id syntax, but the added behavioral framing of the no-id case is genuine value.

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 verb and resource ('End the one-to-one conversation, or leave the queue'), and immediately distinguishes itself from fyreflock_next (end-and-rematch), fyreflock_roost_leave (Roosts) and fyreflock_game_quit (running game). An agent can select it without opening any sibling 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?

Gives an explicit trigger condition ('Only when the person asked to stop, or has clearly moved on to something else') plus named alternatives for each adjacent case: fyreflock_next to end and meet someone else, fyreflock_roost_leave for Roosts, fyreflock_game_quit for a running game. When-to-use and when-not-to-use are both spelled out.

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

All Fyreflock tools Inspect

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.