Skip to main content
Glama

Read a campaign file as LSX

dos2_raw
Read-onlyIdempotent

Converts any binary .lsf campaign file to LSX text, whole or filtered by XPath, for exploring campaign data that structured tools do not expose. Read-only; output can be truncated.

Instructions

Converts any binary campaign file (.lsf) to LSX text and returns it, whole or filtered by XPath. This is the escape hatch for exploring data the other tools do not expose.

Read-only. Prefer the structured tools (dos2_campaign, dos2_scene, dos2_template, dos2_vignettes, dos2_notes)
when they cover the need: raw files are large. With xpath the output starts with a match count; output longer
than max_chars is truncated with a note. Fails with an error if the file does not exist in the campaign.

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": {
      "campaign": "<campaign>",
      "file": "<file>"
    },
    "name": "dos2_raw"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYesPath of the file inside the campaign folder, e.g. "Eggs.lsf", "meta.lsf" or "LevelCache/<scene ID>.lsf".
xpathNoElementTree XPath to return only matching nodes, e.g. ".//node[@id='Note']". Omit to get the whole file.
campaignYesThe campaign to work on: its name, its folder name, its UUID, or a unique part of any of them. dos2_status lists the campaigns.
max_charsNoCut the output to this many characters (default 20000).

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.1
    • addedInput schema / properties / campaign / description
      Added value: +"The campaign to work on: its name, its folder name, its UUID, or a unique part of any of them. dos2_status lists the campaigns."
    • addedInput schema / properties / file / description
      Added value: +"Path of the file inside the campaign folder, e.g. \"Eggs.lsf\", \"meta.lsf\" or \"LevelCache/<scene ID>.lsf\"."
    • addedInput schema / properties / max_chars / description
      Added value: +"Cut the output to this many characters (default 20000)."
    • addedInput schema / properties / xpath / description
      Added value: +"ElementTree XPath to return only matching nodes, e.g. \".//node[@id='Note']\". Omit to get the whole file."
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, and the description reinforces this with 'Read-only.' Beyond that it adds real behavioral detail: xpath output begins with a match count, over-length output is truncated with a note, and a missing file raises an error. It does not describe the LSX text shape, but the existence of an output schema covers that.

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?

Front-loaded with the core verb and resource, then alternatives, then behavioral caveats. Every sentence carries information, though 'Read-only.' is largely redundant with existing annotations and could be folded into the truncation/count sentence.

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?

Given four parameters and an output schema, the definition covers the things an agent would otherwise get wrong: large output, truncation semantics, xpath match counting, and the missing-file error. Nothing critical is absent, though a concrete note on typical output size or LSX structure would round it out.

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 adds operational meaning beyond the schema for two parameters: xpath results are prefixed by a match count, and max_chars causes truncation with a note rather than an error. It does not illustrate accepted xpath syntax or the campaign identifier forms beyond what the schema already says.

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

Purpose5/5

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

States a specific verb and resource (convert a binary .lsf campaign file to LSX text) and immediately positions itself against siblings as 'the escape hatch for exploring data the other tools do not expose.' An agent can tell exactly what this does without opening the schema.

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

Usage Guidelines5/5

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

Explicitly names the preferred alternatives (dos2_campaign, dos2_scene, dos2_template, dos2_vignettes, dos2_notes) and the condition that selects them ('when they cover the need'), plus the caution that raw files are large. The failure condition (file not in campaign) is also stated.

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