Skip to main content
Glama

run_vpk_pack

Packs a staging directory into an addon VPK with the game's vpk.exe, writes the addon manifest if missing, then verifies the archive's entry list against the staging tree to catch dropped files.

Instructions

Packs a staging directory into an addon VPK with the game's own vpk.exe. The directory is packed root-relative, so addoninfo.txt, missions/, maps/ and materials/vgui/maps/ end up where the game expects them. addoninfo writes the manifest first when the directory has none. Afterwards the archive is read back through the sidecar and its entry list is compared with the staging tree: a pack that silently dropped a file is the failure this check exists for.

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": {
      "dir": "<dir>"
    },
    "name": "run_vpk_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
dirYesStaging directory containing addoninfo.txt and the addon's tree.
outNoDestination .vpk. Defaults to <parent>/<directory name>.vpk.
confirmNo
addoninfoNoWrite addoninfo.txt into the staging directory first.
overwriteNo

Output Schema

NameRequiredDescriptionDefault
vpkYes
bytesYes
entriesYes
stagingYes
verifiedYes
entryCountYes
addoninfoWrittenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

B3.4/5.0
Behavior3/5

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

Annotations carry only a title, so the description does the heavy lifting and does add real value: root-relative layout expectations, that addoninfo writes the manifest first when absent, and that the archive is read back and diffed against the staging tree to catch silently dropped files. However it says nothing about what happens on verification failure (error vs. partial output), whether an existing .vpk is replaced, or what confirm/overwrite actually do.

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?

Three sentences, front-loaded with the action and layout, then the manifest write, then the verification step — a logical build order. The closing clause ('the failure this check exists for') is slightly rhetorical but justifies the verification sentence rather than wasting space.

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

Completeness3/5

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

An output schema exists, so return values need not be described, and the core packing behavior is well covered. What is missing is failure semantics (what the entry-list mismatch produces), the effect of overwrite on an existing archive, and the meaning of confirm — significant gaps for a tool that writes files to disk.

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 60%, and the description adds meaning for `dir` (it must contain addoninfo.txt and the addon tree) and for `addoninfo` (written first when the directory lacks a manifest). The `confirm` and `overwrite` parameters have no schema description and no explanation in the description, so the two most behaviorally loaded flags remain opaque.

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 states a specific verb and resource ('Packs a staging directory into an addon VPK') and even names the underlying engine binary, which pins down exactly what the tool produces. It does not explicitly distinguish itself from sibling runners like run_pack or run_pakfile_extract, so an agent must infer that this one is addon-specific.

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 context is implied by 'staging directory' and 'addon VPK', which tells the agent this is the addon-packaging path rather than a generic pack. There is no explicit when-not guidance, no mention of prerequisites (a game install with vpk.exe), and no routing to run_pack or run_pakfile_extract if the agent has a different packing need.

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