Skip to main content
Glama

write_avoid_list

Write the avoid list (negative prompt) for a prompt to guide VACE and LTX dev model rendering away from unwanted elements.

Instructions

Writes the avoid list (negative prompt) for a prompt. Only vace and LTX dev models use it.

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": {
      "image": "<image>",
      "prompt": "<prompt>"
    },
    "name": "write_avoid_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYes
promptYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the agent knows this is a non-destructive write. The description adds genuinely new behavioral context — the value is model-specific and only consumed by vace and LTX dev. It says nothing about whether an existing avoid list is overwritten, whether the write persists across jobs, or what happens if the model is unsupported.

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

Conciseness5/5

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

Two short sentences, zero filler, with the core purpose stated first and the model-restriction qualifier second. Nothing is wasted and nothing important is buried.

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 required-2-parameter write operation with no output schema and no parameter documentation anywhere, the description leaves the agent guessing about the 'image' argument and about overwrite/persistence semantics. The model-applicability note is helpful but does not compensate for those gaps.

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 carries the full burden for both required parameters. It only loosely gestures at 'prompt' and says nothing at all about 'image' — an undocumented required string whose meaning (asset id, path, URL?) is entirely opaque, which is a serious gap for a write tool.

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?

States a specific verb+resource ('Writes the avoid list') and clarifies in parentheses that this is the negative prompt, which distinguishes it from the positive-prompt counterpart. The scope is narrowed further by naming the models that consume it. It never names the sibling that handles the positive prompt, so full sibling differentiation is left implicit.

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

Usage Guidelines3/5

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

The clause 'Only vace and LTX dev models use it' is real conditional guidance that tells the agent when this tool is applicable versus pointless. However, it does not name the alternative tool (write_prompt) for setting the positive prompt, nor does it say what to do for other models — the agent must infer the pairing.

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