Skip to main content
Glama

read_sightlines

Measure the longest unobstructed lines of sight across a compiled map to determine real engagement range. Samples standable ground on a grid and traces each pair against the engine's world tree.

Instructions

Longest unobstructed lines of sight across a compiled map, traced against the same world tree the engine walks for a TraceLine. Samples standable ground on a grid at the elevation where the map's content sits, then measures every pair. Answers 'how far can someone actually see here', which is what sets engagement range. It does NOT know what a street is, and it ignores static props and brush entities (a door counts as open) -- see the excludes field it returns.

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_sightlines"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesPath to the .bsp, absolute or relative to the repo root.
limitNo
spacingNoGrid step in Hammer units. Smaller is finer and quadratically slower.
elevationNoGround elevation to sample. Defaults to the median entity origin z.
eyeHeightNoHeight above ground for the sample point. 64 is a standing player's eye.
elevationToleranceNoHow far a surface may sit from `elevation` and still be sampled.
requireNearbyContentNoKeep only points with a map entity nearby, as a proxy for built-up area.

Output Schema

NameRequiredDescriptionDefault
pathYes
longestYes
spacingYes
excludesYes
elevationYes
pairsTestedYes
samplePointsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

A4.1/5.0
Behavior4/5

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 it well: it discloses the sampling methodology (standable ground on a grid at content elevation, every pair measured) and the blind spots (props and brush entities ignored), and points to the returned `excludes` field. It omits runtime cost, which only the schema hints at via 'quadratically slower'.

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

Conciseness5/5

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

Front-loaded with the outcome, then method, then caveats — three dense sentences with no filler. The negative scoping ('does NOT know what a street is') is placed where it prevents the most likely misinterpretation.

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?

For a compute-heavy analysis tool with an output schema and one required path parameter, the description covers intent, method, and known blind spots, and defers return structure to the output schema by naming the relevant `excludes` field. Nothing an agent needs to invoke 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 86%, so the schema already explains most parameters. The description adds useful framing — grid sampling and the elevation where map content sits — but does not clarify `requireNearbyContent`, `elevationTolerance`, or `eyeHeight` beyond what the schema states.

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 ('measures longest unobstructed lines of sight') and resource ('across a compiled map'), and scopes it to compiled geometry versus the VMF-level sibling by naming the engine's own TraceLine world tree. It also frames the practical question it answers ('how far can someone actually see here').

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?

It implies usage — engagement range analysis on a compiled map — and lists what it deliberately does not model (streets, static props, brush entities, doors count as open), but it never explicitly names an alternative or says when to prefer read_vmf_sightlines over this.

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