Skip to main content
Glama

simulation_stimulate

Destructive

Schedule and deliver calibrated native input events at specified offsets during a live simulation, then save a sampled raw trace for verification.

Instructions

Deliver 1..32 calibrated native input events using a current simulation_inputs token. at_ms is a nondecreasing offset from the current native simulator time. Waits for actual time then dispatches at CURRENT time and records lateness. Delivery delays shift following events enough to preserve requested inter-event spacing, never compress a pulse or inject future events. Native clock is coarse, not hard realtime. BUTTON 0=release/1=press; LOGICSTATE 0=low/1=high. Runtime events only: persistent STATE/icon/disk is not edited. Non-atomic; partial/unconfirmed may have applied; no automatic restore. Dispatched does NOT prove electrical effect or ISR behavior. Saves complete sampled raw trace.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session": "<session>",
      "expected_token": "<expected_token>",
      "events": "<events>",
      "nets": "<nets>"
    },
    "name": "simulation_stimulate"
  }
}

Input Schema

NameRequiredDescriptionDefault
netsYes
eventsYes
sessionYes
timeout_msNo
interval_msNo
expected_tokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds substantial context beyond them: non-atomic execution, partial/unconfirmed application, no automatic restore, timing/lateness behavior, delay propagation that preserves spacing but never compresses a pulse or injects future events, and the caveat that dispatch does not prove electrical effect or ISR behavior. It also notes the trace is saved, which tells the agent how to verify afterward.

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?

Dense and front-loaded — the core action and token requirement come first, followed by timing semantics and then safety caveats. Several clauses are telegraphic to the point of ambiguity ('Non-atomic; partial/unconfirmed may have applied'), but no sentence is padding.

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 destructive, non-atomic mutation with no output schema, the description covers failure semantics, timing behavior, and verification well. The remaining gaps are the concurrency guard (expected_token) and timeout/interval controls, which an agent needs to set correctly and cannot infer from the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across six parameters, so the description carries real weight: it explains value semantics ('BUTTON 0=release/1=press; LOGICSTATE 0=low/1=high'), at_ms as a nondecreasing offset from current native simulator time, and the 1..32 event bound. It leaves nets, session, expected_token, timeout_ms, and interval_ms with no meaning beyond their names, so compensation is only partial.

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 ('Deliver 1..32 calibrated native input events') plus the prerequisite token, and bounds the scope to runtime events by explicitly excluding persistent STATE/icon/disk. That exclusion is what separates it from tooling that edits saved state, so an agent can distinguish it without inspecting the schema.

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 a clear precondition (a 'current simulation_inputs token') and a clear when-not ('Runtime events only: persistent STATE/icon/disk is not edited'), which implicitly routes persistent edits elsewhere. It does not, however, name the alternative tool or state what to do when the token is stale or rejected.

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