Skip to main content
Glama

read_map_dependencies

Resolve every asset a compiled map references and where each comes from at runtime — packed in the BSP, found in game content, or missing — by walking VMT patches, model materials, and skybox sides.

Instructions

Every asset a compiled map references, and where each will come from at runtime: packed inside the map, found in the game's own content, or missing. Missing is the purple checkerboard -- the only failure on this list a mapper never sees at home, because they have the files. The walk is recursive on purpose: it follows VMT patch and include chains, $bottommaterial and $fallbackmaterial, a model's own material list, the skybox's six sides and the detail sprite config. Resolving one level gives a short, plausible, wrong answer. Also separates what is packed but never reached into three groups, because 'unreferenced' is not 'safe to delete': vrad's own output (.vhv, cubemaps) is referenced by the engine and named by no file. Needs the Python sidecar; see health.

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": {
      "path": "<path>"
    },
    "name": "read_map_dependencies"
  }
}

Input Schema

NameRequiredDescriptionDefault
gameNoGame profile id. This fork supports only 'l4d2', which is also the default; any other id is refused rather than answered about the wrong game.
pathYesPath to the .bsp, absolute or relative to the repo root.
limitNoMaximum entries per list. Default 300.

Output Schema

NameRequiredDescriptionDefault
gameYes
pathYes
looseYes
caveatYes
missingYes
bySourceYespacked, game-vpk, game-loose. The last is the one that matters: a loose file resolves at home because it is on that disk and is a checkerboard elsewhere.
resolvedYes
gameErrorYes
notWalkedYes
looseCountYes
modelCountYes
gameMountedYes
missingCountYes
materialCountYes
notWalkedCountYes
optionalAbsentYes
staticPropErrorYes
engineOwnedCountYes
missingTruncatedYes
packedUnreferencedYes
staticPropModelCountYes
packedUnreferencedCountYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

A4/5.0
Behavior4/5

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

Annotations supply only a title, so the description carries the full burden and does so substantially: it discloses a recursive traversal across VMT patch/include chains, $bottommaterial/$fallbackmaterial, model material lists, skybox sides and detail sprites, plus the three-way split of packed-but-unreached content and the sidecar dependency. It omits cost/performance expectations and never states the operation is read-only beyond the name, which keeps it from a 5.

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 definition, then the recursion justification, then the unreferenced-content caveat, then the precondition — a sensible order where each sentence contributes. It is dense and occasionally chatty ('the purple checkerboard', 'vrad's own output'), costing some tightness but not accuracy.

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

Completeness5/5

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

With an output schema present, the description need not explain return shapes, and it covers the remaining unknowns an agent needs: what counts as a dependency, how deep the walk goes, why the recursion matters, what 'missing' looks like in-engine, and the sidecar precondition. Nothing material to calling it correctly is missing.

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

Parameters3/5

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

Schema coverage is 100% and each parameter is self-documented (game profile restriction, path resolution, per-list limit), so the schema does the heavy lifting. The description adds no per-parameter meaning — it never mentions path, game or limit — so the baseline 3 applies.

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?

The opening clause names a specific resource and scope: every asset a compiled map references, classified by runtime origin (packed, game content, missing). That framing distinguishes it from the shallow siblings (read_materials, read_game_content) without needing to name them, and an agent can tell what it returns before 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 Guidelines3/5

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

Usage is implied rather than stated: the recursion rationale ('Resolving one level gives a short, plausible, wrong answer') argues for this tool over a shallow lookup, and 'Needs the Python sidecar; see health' routes the agent to a sibling for a precondition. But there is no explicit when-to-use/when-not statement or named alternative for overlapping cases.

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