Skip to main content
Glama

ghostrigger_call_mcp_tool

Calls any KotorMCP tool by name and arguments to inspect or modify game assets. Use after listing available tools to automate model, module, or dialog queries.

Instructions

Call a KotorMCP tool through GhostRigger's /mcp/tools/call endpoint.

Use ghostrigger_list_mcp_tools() first to discover available tool names and their argument schemas.

Key tool names (see ghostrigger_list_mcp_tools for full list): ghostrigger_open_model — open a model by resref ghostrigger_render_model — render a model to PNG ghostrigger_model_info — get geometry/bone/material info ghostrigger_list_game_models — list all models in the game ghostrigger_audit — audit model for issues kotor_lookup_2da — look up a 2DA table row kotor_lookup_tlk — look up a TLK dialog string kotor_list_modules — list all game modules kotor_describe_module — describe module contents

Args: tool_name: Name of the KotorMCP tool to call arguments: JSON string of arguments (e.g. '{"resref": "n_bastila"}')

Returns: JSON string: {"result": {...}} or {"error": "..."}

KB: see knowledge_base/16_ANIMATION_DEEP_DIVE.md#overview Example: ghostrigger_call_mcp_tool(tool_name="ExampleName")

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
argumentsNo{}
tool_nameYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It states the call returns a JSON string with result or error, but does not disclose side effects, read/write nature, rate limits, or permission requirements. Since it can invoke many tools, the lack of behavioral details (e.g., whether calls are safe or destructive) is a gap.

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?

The description is well-structured and front-loaded with the purpose, then usage guidance, parameter details, return format, and an example. It includes a KB reference and is reasonably concise given the variety of tools it covers, without excessive fluff.

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 generic dispatcher, the description provides sufficient context: return format, example, and pointer to the discovery tool. The KB reference adds value. While it cannot document every sub-tool's arguments, it delegates that to the list tool, making it complete enough for an agent to understand and invoke correctly.

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?

Schema coverage is 0%, but the description compensates by explaining 'tool_name' and 'arguments' with a concrete example and list of possible tool names. It also points to ghostrigger_list_mcp_tools for argument schemas, giving enough context for an agent to construct calls.

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?

The description clearly states the tool calls a KotorMCP tool via an endpoint and lists key tool names, making the purpose specific. It is distinguishable from siblings like 'call_tool' by referencing GhostRigger and KotorMCP, though it doesn't explicitly differentiate from that generic sibling.

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?

The description instructs to use ghostrigger_list_mcp_tools first to discover tool names and schemas, providing clear guidance on when to use this dispatcher. It gives examples of tool names but does not explicitly mention alternative generic call tools or when not to use this one, though the recommendation to list tools first sets expectations.

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