Skip to main content
Glama

delete_solids

Removes brushes from a .vmf by id, owner, material or bounding box, with optional backup and dry-run, so misplaced geometry can be undone instead of staying permanent.

Instructions

Removes brushes from a .vmf. The counterpart of write_vmf_solid, and its absence is what made every mistake permanent: a brush created in the wrong place could not be taken back. Selects by id, owner, material or bounding box, refuses an empty selector rather than emptying the map, and refuses brushes inside a hidden block, whose removal would be as invisible as they are. Warns when the world is left with nothing to seal with, and when a brush entity is left with no brushes at all. It cannot prove the map still seals -- only a compile can.

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": "delete_solids"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesPath to the .vmf, absolute or relative to the repo root.
ownerNo'world', or a brush entity classname such as func_detail.
backupNoCopy the file to <file>.bak before writing. Nothing is copied on a no-op.
dryRunNoCheck and report without writing. Every verification runs either way.
withinNoBrushes lying entirely inside this box. Entirely, not partly: a half-caught brush is how a box selection catches something the caller could not see it had touched.
confirmNoRequired (true) to run this tool: it writes or executes.
materialNoBrushes carrying this on at least one face. Substring, case-insensitive.
solidIdsNoHammer ids, as read_vmf_solids reports them.

Output Schema

NameRequiredDescriptionDefault
pathYes
deletedYes
matchedYes
writtenYes
nextStepYes
warningsYes
unchangedYes
backupPathYes
solidsAfterYes
solidsBeforeYes
worldSolidsAfterYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

A4.5/5.0
Behavior5/5

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

Annotations carry only a title, so the description bears the full burden and delivers: empty-selector refusal, hidden-block refusal, warnings for an unsealed world and emptied brush entities, and an explicit caveat that it cannot prove the map still seals. It also frames the destructive, irreversible nature of the operation.

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?

Purpose and selector semantics are front-loaded in the first sentences, followed by refusal and warning behavior. A few clauses are rhetorical ('whose removal would be as invisible as they are', 'its absence is what made every mistake permanent') and cost tokens without adding call guidance, but the overall shape is efficient.

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?

An output schema exists, so return values need no explanation, and the description covers selection, refusals, and warnings for a destructive 8-parameter tool with nested objects. It omits the confirm gate, backup, and dryRun semantics, which an agent must still learn from the schema alone.

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 cross-parameter meaning the schema cannot express: the four selector fields are alternatives and at least one must be present, and deletion is idempotent-aware ('nothing is copied on a no-op' is in schema only). It does not explain confirm/backup/dryRun behavior in prose.

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?

Opens with a specific verb+resource ('Removes brushes from a .vmf') and explicitly frames itself as 'the counterpart of write_vmf_solid', so the agent can place it against the writer without opening schemas.

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?

Gives clear operational guidance: it selects by id/owner/material/bbox, refuses an empty selector rather than emptying the map, and refuses brushes in hidden blocks. It does not name a sibling alternative to use instead (e.g. clip_solids or transform), so it stops short of full when/when-not routing.

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