Skip to main content
Glama
Sign In
Houdini MCP

Houdini MCP

by beatreichenbach
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

dirty_work_items

Marks work items on a TOP node as dirty so they can be regenerated, optionally removing outputs.

Instructions

Dirty work items on a TOP node so they can be regenerated.

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": {
      "node_path": "<node_path>"
    },
    "name": "dirty_work_items"
  }
}

Input Schema

NameRequiredDescriptionDefault
node_pathYes
remove_outputsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.4/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden. "Dirty" implies a state mutation on the node's work items, but the description never says the prior cook results are invalidated, whether the change is reversible, or that remove_outputs can delete cached outputs. The potentially destructive removal behavior is completely undisclosed.

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

Conciseness3/5

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

A single front-loaded sentence with no filler, which is structurally sound. But the brevity here is under-specification rather than efficiency — the sentence is too short to convey what the operation actually does to the work items.

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

Completeness2/5

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

For a mutating tool with no annotations, no output schema, and two completely undocumented parameters, the description should explain side effects, the effect on cached results, and what is returned. None of that is present, leaving the agent unable to predict the consequences of the call.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate and it does not. "On a TOP node" gives minimal context for node_path, but remove_outputs (which presumably deletes existing output files) gets no explanation of what it removes or when to enable it.

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

Purpose3/5

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

"Dirty work items on a TOP node" names a specific verb and resource, and the qualifier "so they can be regenerated" hints at the outcome. However "dirty" is PDG jargon that an unfamiliar agent may not interpret as marking items stale, so the effect is only vaguely conveyed. Sibling get_failed_work_items is a different population of items, but the description never explicitly contrasts the two.

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

Usage Guidelines2/5

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

The only usage signal is the trailing clause "so they can be regenerated", which implies the call precedes a regeneration step. There is no statement of prerequisites (is the node mid-cook? must the graph be paused?), no exclusion telling the agent when not to dirty items, and no pointer to an alternative such as regenerating the whole TOP node.

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

Deploy Server

Other Tools