Skip to main content
Glama

read_nav_dump

Reads a generated nav mesh's _nav.txt dump to list each area's centre, connections and decoded flags. Use it to verify offline that the mesh has a goal area and escape flow the Director can run.

Instructions

Reads the <map>_nav.txt dump the engine writes beside a generated nav mesh: every area's centre, its connections, and its attribute flags decoded — CHECKPOINT, PLAYER_START, FINALE and the computed escape route. Answers whether the mesh is a map the Director can run (a goal area plus a flow path) without loading the game. The dump is text; the .nav binary layout is not parsed here.

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_dump"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesPath to the <map>_nav.txt dump.
limitNoAreas to return.
offsetNoAreas to skip.

Output Schema

NameRequiredDescriptionDefault
pathYes
areasYes
summaryYes
verdictYes
returnedYes
areaCountYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

A4.2/5.0
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 full burden. It discloses that the operation is a read, that it works on the text dump rather than the binary, and that it avoids loading the game, plus what the output contains. It does not state what happens if the dump file is missing or how limit/offset pagination behaves.

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?

Three tight sentences, front-loaded with what the dump contains before the payoff (whether the Director can run the map). The closing note about the .nav binary is short and does real disambiguation work, so no sentence is wasted.

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 the description need not explain return values, yet it usefully characterizes the content anyway. The main remaining gap is behavior on missing or malformed dump files and pagination, which matters for a file-reading tool but is a minor omission given full schema coverage.

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 each of the three parameters (path, limit, offset) is documented in the schema. The description adds no syntax, path-resolution, or pagination semantics beyond what the schema already provides, so the baseline of 3 applies.

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?

The description names a specific verb and resource (reads the `<map>_nav.txt` dump the engine writes beside a generated nav mesh) and enumerates its contents: area centres, connections, and decoded attribute flags (CHECKPOINT, PLAYER_START, FINALE, escape route). It also distinguishes itself from binary nav parsing by stating the .nav binary layout is not parsed here, which separates it from a sibling like read_nav.

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?

It gives clear usage context: use this to answer whether the mesh is a map the Director can run (goal area plus flow path) without loading the game. The exclusion of binary .nav parsing implicitly routes binary questions elsewhere, but no sibling tool is named explicitly and no prerequisites are stated.

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