Skip to main content
Glama
Sign In

SimianX AI

by io.github.SimianX-AI
OverviewDiscussionsAdmin

Get what the user has not heard yet

get_updates
Read-onlyIdempotent

Every update of this key the user has not been told: finished analysis steps, decisions (with the question to ask), matched news. Relay each say (and ask) in order, then call again with ack set to the last id you relayed; unacked updates come back until you do. Use wait (up to 25 s) to hold for the next one, and keep calling while any run or session is open.

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": "get_updates"
  }
}

Input Schema

NameRequiredDescriptionDefault
ackNoLast update id you relayed to the user
waitNoSeconds to wait for something new before answering, 0-25
afterNoOnly ids above this (default 0)
kindsNoComma-separated kinds
limitNoRows, up to 100 (default 50)
notifyNotrue: only what the user must hear

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), but the description adds the critical at-least-once semantics: unacked updates keep coming back until acknowledged. That delivery guarantee and the 25-second blocking behavior are things an agent cannot infer from the annotations and are essential for correct looping.

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?

The payload is front-loaded and dense: content types first, then the ack→re-call loop, then wait behavior. The opening clause 'Every update of this key the user has not been told' is slightly awkward, but no sentence is wasted.

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?

For a 6-parameter polling tool with no output schema, the description covers the delivery protocol and return content (say/ask, ids) well enough to call it correctly. It does not touch the filtering/pagination levers (`after`, `kinds`, `limit`, `notify`), though those are fully schema-documented.

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, but the description adds real semantics for `ack` (the id of the last item relayed, and the consequence of not sending it) that go beyond the schema's terse 'Last update id you relayed'. `wait` is also given operational meaning ('hold for the next one'). `after`, `kinds`, `limit`, and `notify` are left entirely to the schema.

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?

The description states the resource precisely (per-key undelivered updates) and enumerates what kinds of content come back: finished analysis steps, decisions with questions, matched news. It does not explicitly distinguish itself from polling-adjacent siblings like analysis_live_list or get_pulse_events, but the 'user has not heard yet' framing makes its role identifiable.

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?

It gives an explicit operating protocol: relay each `say`/`ask` in order, then re-call with `ack` set to the last relayed id, and keep calling while any run or session is open. It also names the alternative mode (`wait` up to 25s to hold for the next one), so the agent knows both when to poll actively and when to block.

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

All SimianX AI toolsInspect
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.

Resources