Skip to main content
Glama

read_nav

Reads a .nav mesh header and compares it to its map's BSP size to catch mismatches that silently break Nextbot pathing. Run it after every map compile, which invalidates nav.

Instructions

Reads a .nav mesh header and says whether it still matches its map. The engine compares the BSP size recorded in the mesh against the map it is loading, and a mismatch means the mesh is silently unusable -- in game that looks like Nextbots that will not path, with nothing in the console explaining why. Recompiling a map always invalidates its nav, so check this after any compile. Generating a new one needs the engine (nav_generate); there is no offline generator, in this project or anywhere public.

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_nav"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesThe .nav, or the .bsp beside it.

Output Schema

NameRequiredDescriptionDefault
bspYes
pathYes
verdictYes
versionYes
areaCountYes
fileBytesYes
isAnalyzedYes
matchesBspYes
placeCountYes
subVersionYes
savedBspSizeYes
actualBspSizeYes

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 bears the load and does well: it explains the engine's BSP-size comparison, that a mismatch is silent at runtime, and what the failure looks like in game (Nextbots that will not path, empty console). It never explicitly states the tool is strictly read-only and has no side effects, which is the one gap.

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 what it does and why it matters, and every sentence adds new information (mismatch semantics, compile invalidation, no offline generator). It runs four sentences where three would do, but nothing is filler.

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-value detail is unnecessary, and the description covers the failure mode an agent most needs to interpret a negative result. The remaining gap is the absence of any explicit read-only/scope statement to compensate for thin annotations.

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 100% and the single parameter is documented as "The .nav, or the .bsp beside it," so the schema already resolves ambiguity about which file to pass. The description adds only that it reads the mesh header, which is baseline-level value at best.

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 and resource ("Reads a .nav mesh header") plus a precise outcome ("says whether it still matches its map"). It also implicitly separates itself from read_nav_dump by scoping to the header and a validity check, and names nav_generate for the different job of creation.

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 an explicit trigger — "check this after any compile" — because recompiling invalidates nav data. It also routes generation to the engine (nav_generate) and rules out an offline path. It stops short of naming read_nav_dump as the alternative when the full mesh contents, not validity, are wanted.

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