mcp-server

Hands Triggers

alterlab_hands_triggers

Triggers start a delegated Hands run when a source fires: a monitor change, a schedule, an inbound message, a webhook, a fact change or a user command. A trigger with a condition (for example price below a threshold) fires only after the observed value is confirmed by a second agreeing observation; a single glitch never fires. The user's approval policy is evaluated at firing time, so tightening it after creation blocks the action. Each trigger has a rate limit, an optional per-firing spend limit and a circuit breaker that disables it after N consecutive failures and notifies the user. action=create adds a trigger; action=list lists them; action=pause, resume and revoke change one (revoke is one call and final); action=firings returns the audit of observations and decisions.

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": "alterlab_hands_triggers"
  }
}

Input Schema

Name	Required	Description
`label`	No	Create: a name for the trigger
`limit`	No	Firings: rows to return
`action`	No	Default list
`condition`	No	Create: subject, key, op (lt\|lte\|gt\|gte\|eq\|changed), threshold, kind, currency, confirmations (min 2)
`interval_s`	No	Create: seconds between runs for a schedule source
`source_ref`	No	Create: monitor id or mailbox address the source watches
`trigger_id`	No	Required for pause, resume, revoke and firings
`source_type`	No	Create: what fires it
`spend_limit`	No	Create: most one firing may spend, in currency
`run_template`	No	Create: start_url, allowed_domains, instruction, mode, risk_class, recipe, ttl_s
`breaker_threshold`	No	Create: consecutive failures before it disables
`rate_limit_per_hour`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond annotations, the description discloses real behavioral traits: the two-observation confirmation rule that suppresses single glitches, approval policy evaluated at firing time (so tightened policy blocks later firings), rate limits, per-firing spend caps, and a circuit breaker that disables after N consecutive failures and notifies the user. The one tension is that it states 'revoke is one call and final' while annotations declare destructiveHint=false; that reads as an under-declared annotation rather than a description error, so it is not scored as a contradiction.

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?

It is a dense single paragraph but effectively front-loaded: purpose first, then firing semantics, then the action dispatch list. Nearly every clause carries information, though the action mapping at the end would be easier to scan if it were not buried in prose.

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 12-parameter, multi-action tool with nested objects and no output schema, the description covers the semantics an agent needs: what fires, what gates firing, what limits apply, and what each action does. It stops short of describing what create or firings return and how `limit` paginates the audit, which an agent would want.

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?

With 92% schema coverage the schema already documents most fields, so the baseline is 3; the description earns above that by explaining the meaning behind fields the schema only names – what `condition` confirmation actually does at fire time, what the breaker threshold triggers, and what spend_limit constrains per firing. It does not, however, explain the nested `run_template` or `condition` sub-fields beyond what the schema lists.

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?

The first sentence names a specific verb and resource (triggers start a delegated Hands run) and enumerates the six source types that fire them, which cleanly separates it from sibling run/schedule tools. The final sentence then maps every enum value of `action` to a concrete operation, so there is no ambiguity about what a call does.

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?

Usage is spelled out per action: create adds, list enumerates, pause/resume/revoke change one, firings returns the audit, and revoke is called out as final. What is missing is routing against siblings – nothing says whether to use this or alterlab_schedule / alterlab_monitor / alterlab_hands_run for a one-off or a recurring run.

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

All mcp-server 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.