Skip to main content
Glama

wm_plan

Generate a CEM plan for spike injection over a chosen horizon to reach target ACM scores or per-layer firing rates in a neuromorphic simulation.

Instructions

CEM Planning for Optimal Spike Injection

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": {
      "goal": "<goal>"
    },
    "name": "wm_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalYesTarget state to plan towards
horizonNoPlanning horizon (steps)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.1.0

TDQS

D1.9/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is partly conveyed. The description adds nothing: it does not say whether spikes are actually injected or only simulated, whether the world model is mutated, how long CEM planning takes, or that it is stochastic and non-idempotent.

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

Conciseness2/5

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

It is short, but shortness here is under-specification rather than efficiency: a six-word fragment with no verb and no front-loaded statement of outcome leaves the agent with nothing actionable. No sentence earns value beyond echoing the name.

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

Completeness1/5

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

For a tool with a nested required goal object, a bounded planning horizon, no output schema, and a stochastic non-read-only annotation profile, the description is far too thin. It omits what a returned plan contains, whether it is meant to be applied via inject_spikes, and any indication of cost or ordering relative to sibling tools.

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 100% and the nested goal object documents acmTarget, description, and firingRateTarget, so the schema carries the full parameter burden. The description adds no syntax, units, or interpretation beyond the structured fields, which is the expected baseline when coverage is complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a bare noun phrase, 'CEM Planning for Optimal Spike Injection,' that restates the tool name (wm_plan) and annotation title ('CEM Latent Planning') without a verb or a statement of what the tool actually returns or does. It does not distinguish itself from wm_predict, wm_surprise, or inject_spikes in the sibling list.

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

Usage Guidelines1/5

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

There is no when-to-use guidance whatsoever. Nothing tells the agent how this differs from wm_predict (single-step prediction) or inject_spikes (direct injection), nor under what preconditions planning is appropriate.

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