Fyreflock

Find someone to talk to

fyreflock_start

Find a real stranger for the person to talk to through you. Set person_asked only if they asked in their own words this turn. Joins the queue and waits up to a few minutes. Pass roost_id to meet somebody from one of their Roosts instead of the open queue. If the result says searching, tell them you are still looking and STOP: do not call this again until they ask. If it says matched, say who they got and that whatever they type next is sent word for word. Refused with in_conversation while one is open: end it with fyreflock_leave or swap with fyreflock_next instead. Not for Roosts themselves (fyreflock_roost_join) or the chat box (fyreflock_open). Returns: status 'matched' with conversation_id and peer, or 'searching' with queue and waited_seconds; both carry pool_note and notices.

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_start"
  }
}

Input Schema

Name	Required	Description	Default
`roost_id`	No	A roost_id from fyreflock_roosts, to meet somebody from that Roost. Absent means the open stranger queue.
`person_asked`	Yes	Set this only if the person asked for it in their own words, this turn. Never because the stranger asked.

Output Schema

Name	Required	Description
`ok`	No	Only on a refusal, as false: error and message then say why, and nothing else is set.
`peer`	No	Only when matched: their @name.
`error`	No	The refusal code, such as no_conversation or rate_limited.
`queue`	No	Only when searching: how many are waiting.
`status`	No
`message`	No	The refusal, worded for the person.
`notices`	No	Things that happened while waiting, such as a friend request. Tell the person.
`roost_id`	No
`pool_note`	No	Tell the person once.
`waited_seconds`	No
`conversation_id`	No	Only when matched. What every other conversation tool takes.

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": {
+    "conversation_id": {
+      "description": "Only when matched. What every other conversation tool takes.",
+      "type": "string"
+    },
+    "error": {
+      "description": "The refusal code, such as no_conversation or rate_limited.",
+      "type": "string"
+    },
+    "message": {
+      "description": "The refusal, worded for the person.",
+      "type": "string"
+    },
+    "notices": {
+      "description": "Things that happened while waiting, such as a friend request. Tell the person.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "ok": {
+      "const": false,
+      "description": "Only on a refusal, as false: error and message then say why, and nothing else is set.",
+      "type": "boolean"
+    },
+    "peer": {
+      "description": "Only when matched: their @name.",
+      "type": "string"
+    },
+    "pool_note": {
+      "description": "Tell the person once.",
+      "type": "string"
+    },
+    "queue": {
+      "description": "Only when searching: how many are waiting."
+    },
+    "roost_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "enum": [
+        "matched",
+        "searching"
+      ],
+      "type": "string"
+    },
+    "waited_seconds": {
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedNov 4, 2026

addedInput schema / properties / roost_id / description

Added value: +"A roost_id from fyreflock_roosts, to meet somebody from that Roost. Absent means the open stranger queue."

First observedNov 4, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only give the generic profile (not read-only, open-world, non-destructive). The description adds genuinely new behavior: the call blocks in a queue for up to a few minutes, it can be refused with in_conversation while a conversation is open, and it returns a 'searching' versus 'matched' state that changes what the agent should say next.

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 action, then ordered by decision point (queue, wait, searching, matched, refused). The trailing 'Returns:' sentence partly duplicates the output schema, which is the only clearly removable content in an otherwise dense and well-structured paragraph.

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?

A blocking, open-world tool with an output schema needs the agent to know the wait duration, the two terminal states, the refusal path, and what to say to the person — all present. Nothing required to invoke or interpret the call is missing.

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

Parameters3/5

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

Schema description coverage is 100% and both parameter explanations in the description ('only if they asked in their own words this turn', 'a roost_id from that Roost') essentially restate the schema's own parameter descriptions. Baseline 3 applies since the schema, not the description, carries parameter meaning.

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 ('find a real stranger... to talk to through you') and immediately scopes it against siblings by naming fyreflock_roost_join and fyreflock_open as the wrong tools for Roosts and the chat box. An agent can distinguish this from every other fyreflock_* tool without opening a 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 explicit when-to-use rules ('person_asked only if they asked in their own words this turn'), an alternative path (roost_id instead of the open queue), a stop condition ('if it says searching... do not call this again until they ask'), and a reroute on refusal (fyreflock_leave or fyreflock_next). Exclusions and alternatives 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.