Skip to main content
Glama

check_vmf_rules

Validates a .vmf against its map-specific .rules.json, reporting rule violations with worst points or skipped rules when no rules file exists.

Instructions

Checks a .vmf against ITS OWN rules file -- <map>.rules.json, a sibling of the .vmf. 'Four metres of pavement, no entrance obstructed, the view from the lobby preserved' is a design brief, and this is the form of it a machine can check. Per map and never global: a residential street and a warehouse have different right answers for every number, and a shared default would be wrong for both while looking authoritative. No rules file means NO checking, not checking against something reasonable. It REPORTS: the writing tools do not consult it and must not, because a mapper may want a narrow alley. Every violation carries the worst point, so render_vmf_view or render_vmf_plan can be pointed straight at it. Read overall, not errorCount: a run in which some rule matched nothing comes back 'skipped', never 'pass'.

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": "check_vmf_rules"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesPath to the .vmf, absolute or relative to the repo root.
stepNo
limitNo
seedsNoPoints inside the map, for rules about rooms. Default: the spawn entities.
maxCellsNo
severityNoReport only violations at least this severe.all
eyeHeightNoHeight above each end's origin that a sightline is traced at. Source's own eye is 64. It is in every sightline violation's message, because a rule that fails on a lintel is otherwise indistinguishable from one that fails on a wall.
rulesPathNoOverride the sibling file. There is no search up the directory tree.
minRoomAreaNoBelow this floor area, in square units, a region is merged into its largest neighbour. The same knob read_vmf_rooms takes: pass both the same value, or a diagnosis and the verdict it explains are about different segmentations.

Output Schema

NameRequiredDescriptionDefault
pathYes
notesYes
overallYes
reportedYes
rulesPathYes
errorCountYes
rulesFoundYes
violationsYes
rulesCheckedYes
segmentationYes
warningCountYes
matchedNothingYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

A3.8/5.0
Behavior4/5

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

Annotations contain only a title, so the description carries the full load and does so well: it discloses the skipped-versus-pass status semantics, that no rules file disables checking entirely, that violations carry a worst point usable as a camera target, and that the tool is non-authoritative for writers. It does not mention cost or that large maps may be bounded (the maxCells parameter hints at this), leaving some operational behavior implicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core constraints are front-loaded in the first two sentences, but the 'four metres of pavement... design brief' analogy and the rhetorical 'wrong for both while looking authoritative' consume space without adding operable information. The closing `overall` vs `errorCount` note is genuinely useful and should have been given more prominence instead.

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?

With an output schema present, the description need not explain return shapes, yet it still supplies the one non-obvious reading rule (`overall` over `errorCount`). For a nine-parameter diagnostic tool, the explanation of scope, gating, and reporting posture is nearly complete; only the relationship to the rules-file format itself is left unstated.

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 description coverage is 67%, so roughly a third of the nine parameters carry no explanation in either place, and the description adds no parameter-level detail of its own. The closest it comes is reinforcing the per-map rules concept that underlies rulesPath, but the schema already states that override and the no-directory-search rule.

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 names a specific verb and resource — 'Checks a .vmf against ITS OWN rules file' — and pins down the rules-file scope as a sibling `<map>.rules.json`. It distinguishes itself from the writing tools but never mentions the sibling `read_vmf_lint`, so an agent must infer the difference between rules-based checking and general linting.

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?

Strong conditional guidance: 'No rules file means NO checking, not checking against something reasonable' tells the agent exactly when the tool is a no-op, and the emphasis that it only REPORTS ('the writing tools do not consult it and must not') clarifies it is a diagnostic rather than a gate. It also routes output consumption ('Read `overall`, not `errorCount`') and points to render_vmf_view/render_vmf_plan for visualization, though it omits an explicit comparison against read_vmf_lint.

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