Skip to main content
Glama
JSungMin

vs-token-safer

vts_setup

Configure project path, backend, and max results for token-safe code search. Optionally generate the C++ compile database for clangd semantic search.

Instructions

Configure vs-token-safer (projectPath, backend, maxResults). Writes ~/.vs-token-safer/config.json; run /reload-plugins after. Precedence: env (VTS_*) > config file > default. Can also generate the C++ compile DB in the same step (genCompileDb).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectPathNoDefault project root.
backendNoclangd | roslyn | typescript | pyright (default: auto).
maxResultsNoDefault cap on returned locations.
genCompileDbNoGenerate the C++ compile_commands.json (for clangd semantic search) in this step: `true` = DRY-RUN (prints the exact UBT command, runs nothing); "apply" = run UBT now (heavy — indexes engine headers, needs clangd ≥ 22). The DB is parked out-of-tree (~/.vs-token-safer/db/<project>).
clangdCmdNoPath to the clangd ≥ 22 binary to use (persists to config, no OS-env edit). The VS-bundled clangd 19.1.x deadlocks on Unreal TUs — point this at a current clangd from https://github.com/clangd/clangd/releases. Env VTS_CLANGD_CMD overrides it.
Behavior4/5

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

Without annotations, description bears full burden. It discloses file write, required post-action, and detailed behavior of genCompileDb parameter (dry-run vs apply with heavy indexing). Could mention if it overwrites existing config or permission requirements.

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 sentences, front-loaded with core function, followed by side effect and optional feature. No redundant words.

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?

Covers main functionality and combined use well. Mentions post-action and precedence. Could be improved by noting that separate sibling tools exist for granular control.

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 100%, so baseline 3. Description repeats parameter names and adds minimal extra meaning beyond schema, which already provides detailed descriptions for genCompileDb and clangdCmd.

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?

Description clearly states it configures vs-token-safer and can optionally generate a C++ compile DB, distinguishing it from sibling tools like vts_config and vts_gen_compile_db which handle each task separately.

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?

Provides clear context: writes config file, requires /reload-plugins after, and mentions environment precedence. However, it does not explicitly state when to use this tool versus the more specialized siblings vts_config or vts_gen_compile_db.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JSungMin/vs-token-safer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server