AgentX

list_agents

Read-onlyIdempotent

List the agents you can reach, a page at a time, each with the name to use when messaging it and the machine it runs on. Call this first — the names it returns are exactly what send_message, check_agent_output and interrupt_agent expect. People in the tenant are in the same list, marked kind: "human", and are messaged by name the same way.

Each row is a short summary; call get_agent with a name for the full record. Most recently active agents come first; the order may shift while agents work, so re-list from the start to refresh. The result carries total and, when more remain, next_cursor — pass it as cursor for the next page. Use query to find an agent by name. An empty list means the user has no agents yet; agents are created in the AgentX web dashboard, not from here. No busy/idle status is shown: an agent can work in several chats at once, and a message to a busy agent is queued and answered.

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": "list_agents"
  }
}

Input Schema

Name	Required	Description
`query`	No	Part of an agent's name to search for, case-insensitive.
`cursor`	No	The next_cursor returned by the previous list_agents page.
`page_size`	No	Most agents to return. Defaults to 20, at most 50.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare read-only/idempotent, so the description safely spends its words elsewhere: ordering is most-recently-active first and can shift mid-work, re-list from the start to refresh, and there is deliberately no busy/idle status because messages to busy agents are queued. Those are non-obvious traits an agent could otherwise misread as a bug.

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 purpose and the 'call this first' rule, then pagination, then edge cases; nearly every sentence carries new information. It runs slightly long and repeats cursor semantics already in the schema, which keeps it from a 5.

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 three-optional-parameter list tool with no output schema, the description covers ordering, paging, refresh behavior, empty-state meaning, human entries via `kind: "human"`, and the absent status field. An agent can call it and interpret the response with nothing left to guess.

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 earns a step more by describing the pagination contract end-to-end — result carries `total` and `next_cursor`, which is passed back as `cursor`, and `query` matches by name. It does not add much syntax detail beyond the schema, hence not a 5.

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 ('List the agents you can reach') plus the shape of each row (name for messaging, host machine). It clearly distinguishes itself from get_agent ('for the full record') and from the messaging siblings whose name arguments depend on this output.

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?

Explicitly says 'Call this first' and names the three siblings whose inputs come from this output. It also routes the agent to get_agent for detail, to the web dashboard for creating agents, and explains what an empty list means — when/when-not coverage is unusually complete.

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

All AgentX 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.