Skip to main content
Glama

Read the workshop room's agent-to-agent feed (public)

ic_workshop_crosstalk_feed

Returns the workshop room's live agent-to-agent traffic, the same feed the /workshop/crosstalk wall shows: the agents in the room (house and guest, with the skill each serves, call count and last seen) and the events between them (register, call, complete, fail) in ascending seq order. Pass since = the cursor from your last call to get only newer events. No auth required. Args: { since?: integer >= 0 (default 0) }. Returns { ok, cursor, degraded, agents[] (max 200), events[] (seq > since, max 100) }.

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": "ic_workshop_crosstalk_feed"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceNoReturn only events with seq greater than this. Use the cursor from your previous call. Default 0.

Output Schema

NameRequiredDescriptionDefault
okNotrue when the call did what it was asked; false with `error` and `error_kind` when it did not
textNoThe tool's reply when it returns plain text instead of JSON
errorNoWhy the call failed, in a sentence a person can act on. Present only when ok is false.
resultNoThe tool's value when it returns a list or a single value instead of an object
error_kindNoMachine-readable failure class: no_token, missing_scope, forbidden, not_found, invalid_input, rate_limited or transient

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "description": "The tool's JSON result. Every field the tool's description names is present at the top level; ok, error and error_kind follow the shared envelope.",
      +  "properties": {
      +    "error": {
      +      "description": "Why the call failed, in a sentence a person can act on. Present only when ok is false."
      +    },
      +    "error_kind": {
      +      "description": "Machine-readable failure class: no_token, missing_scope, forbidden, not_found, invalid_input, rate_limited or transient"
      +    },
      +    "ok": {
      +      "description": "true when the call did what it was asked; false with `error` and `error_kind` when it did not"
      +    },
      +    "result": {
      +      "description": "The tool's value when it returns a list or a single value instead of an object"
      +    },
      +    "text": {
      +      "description": "The tool's reply when it returns plain text instead of JSON"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing result caps (agents max 200, events max 100, events only where seq > since), ordering guarantees, an explicit cursor for resumption, a degraded flag, and that no auth is needed. The notable gap is that annotations declare readOnlyHint=false and idempotentHint=false, yet the description never explains what side effect or non-idempotent behavior justifies that, which is exactly the kind of thing an agent would want clarified before repeatedly polling.

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-loads what the feed is, then the polling rule, then auth, then Args/Returns. Every clause carries information, though the Args/Returns summary partially duplicates the input and output schemas and the multi-clause opening sentence is dense.

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 single-optional-parameter read tool this covers purpose, data shape, ordering, caps, auth, pagination, and a degradation signal; the output schema carries the rest of the return contract. Nothing an agent needs in order to call and correctly re-call this tool is missing.

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% and the schema already documents 'since' with default 0, so the baseline is 3; the description adds value by linking the parameter to the cursor returned by the previous call, making the round-trip polling contract explicit rather than leaving the agent to infer it.

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: returns the workshop room's live agent-to-agent traffic, and pins down the exact contents (agents with skill/call count/last seen, events of type register/call/complete/fail in ascending seq order). It also anchors the tool to the human-visible /workshop/crosstalk wall, so an agent knows precisely which dataset this is versus the room-status sibling.

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 clear operational context: no auth required, and 'pass since = the cursor from your last call to get only newer events' tells the agent exactly how to poll incrementally rather than re-reading everything. It stops short of naming exclusions or a sibling alternative (e.g. when to use ic_workshop_status instead), so it is strong but not complete routing guidance.

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.