Skip to main content
Glama

selftest

Verifies Nexus Relay's Codex and Antigravity interfaces and runs an end-to-end wake test to a chosen agent, confirming message delivery, reply correlation, and duration.

Instructions

Relay self-test: interface landmarks of Codex and Antigravity (expected buttons and menus found), then, with to, a real end-to-end wake: test message from you to to, wake, read, correlated reply, duration. Returns the table of the directions from the host (Claude by default) to the agents it can wake.

Args: to: recipient to test ("codex" or "antigravity"); omitted = landmarks only. timeout_s: maximum wait for the reply (60 to 600 s).

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": "selftest"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNo
timeout_sNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.8.7
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "result": {
      -      "title": "Result",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "result"
      -  ],
      -  "title": "selftestOutput",
      -  "type": "object"
      -}New value: +null
  2. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Goes beyond annotations by disclosing that the `to` mode actually sends a test message to another agent and waits for a correlated reply, i.e. it touches live agents rather than only reading local state. It also gives the timeout bounds (60–600 s), useful context for a non-readOnly, non-idempotent operation. It does not state whether the test message is visible/side-effecting on the recipient beyond the wake.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the mode distinction, which is good, but the first sentence is a dense run-on mixing landmarks, wake, reply correlation and duration. The 'Args:' block duplicates schema fields and the default timeout is never stated, so it is uneven rather than wasteful.

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

Completeness4/5

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

No output schema exists and the description does mention the return value (a table of directions from the host to wakable agents), which covers the key output question. Remaining gaps are minor: what a failed landmark check looks like and whether the test message is retrievable by the recipient afterward.

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 0%, so the description carries the burden and mostly does: it names the permitted values 'codex' or 'antigravity' (an enum the schema lacks) and the timeout range 60–600 s. It omits the default of 420 s and does not say what happens with an invalid recipient.

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?

States a specific action: a relay self-test that checks interface landmarks of Codex/Antigravity and optionally performs a real end-to-end wake with a correlated reply. The verb+resource are identifiable, but jargon like 'interface landmarks' is undefined, so the agent must infer what is actually verified.

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

Usage Guidelines3/5

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

The description does explain the two modes ('omitted = landmarks only' vs. passing `to` to run a real wake), which is genuinely useful. It never contrasts with the many sibling diagnostics (status, survey, where, progress), so an agent has no explicit rule for choosing selftest over those alternatives.

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