ScoreIA La Forge

lice_run

Send the whole run of your knight for one pass: frames = {"1": {part_id: {position?, rotation?}}, ...} up to frame 64 (0.25 s apart), poses in the lane's frame (start at z 0, finish line at z 10; frame 0 is your forged pose; a part keeps its last pose). The first pass locks your knight. Returns the full judgement: distance, where and why the run stopped, posts cut, bell, blows, wet feet and your trunk's path. After the third pass the card is sealed.

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": {
      "forge_handle": "<forge_handle>",
      "frames": "<frames>"
    },
    "name": "lice_run"
  }
}

Input Schema

Name	Required	Description	Default
`frames`	Yes	{"1": {"cuirass": {"position": [0, 1.2, 0.2]}, ...}, "2": {...}}
`forge_handle`	Yes	The forge_handle returned by enter_forge.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Adds substantial behavior beyond the annotations: the first pass locks the knight, the third seals the card, frames are capped at 64 with 0.25 s spacing, poses use lane coordinates, frame 0 is the forged pose, and parts carry their last pose. It also discloses the returned judgement fields, which is valuable because there is no output schema.

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 paragraph is front-loaded with the action and packs frame rules, state effects, and return fields into a small space. It is dense and semicolon-heavy, and the themed result vocabulary is slightly harder to parse, but almost every sentence carries useful information.

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 two-parameter mutation with no output schema, it covers the submission format, lock/seal state transitions, and returned judgement content. It leaves out error or validation behavior and does not explicitly connect to forge_handle or status siblings, which are minor operational gaps.

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 100%, so the baseline is 3, but the description meaningfully enriches the frames parameter with the frame cap, timing, coordinate frame, z endpoints, frame-0 semantics, and last-pose carryover. It does not expand on forge_handle, though the schema already identifies it as the handle returned by enter_forge.

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 the specific action: submitting the whole knight run for one pass, with frame data and pass limits. It does not name siblings such as lice_status or lice_seal, so differentiation comes only from the implied lock/seal mechanics rather than explicit comparison.

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 establishes clear pipeline context: the first pass locks the knight and the third pass seals the card. It does not explicitly route the agent to enter_forge for the handle or say when to check status or seal, so alternatives remain implicit.

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

All ScoreIA La Forge tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?