Skip to main content
Glama

Get vimrc

get_vimrc
Read-only

The vimrc of the tracker's vi mode — the caller's own, or with 'projectKey' that project's, which lies over its members' own (order: vim's defaults, the person's vimrc, the project's vimrc, then ':set' on one device). Answers 'vimrc', 'warnings' (each {line, kind, word, message}: a line the editor will not read) and, for your own, 'ignoreProjectVimrc' (projects' vimrcs do not apply to you); for a project, 'canEdit'. Anybody who sees the project may read its vimrc. Read: 'set' with number (nu), hlsearch (hls), incsearch (is), ignorecase (ic), smartcase (scs), wrapscan (ws) and clipboard=unnamed|unnamedplus in vim's spellings (no…, inv…, !, &); 'syntax on|off'; 'let mapleader = ","'; and map, nmap, vmap, xmap, imap, noremap, nnoremap, vnoremap, xnoremap, inoremap of plain keys and . Comments (") and blank lines are fine. Any other line is not an error: it is kept, skipped by the editor and named in 'warnings' with its line.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_vimrc"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectKeyNoA project key, e.g. 'PM', for that project's vimrc. Left out: your own.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior5/5

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

With readOnlyHint and destructiveHint already covering safety, the description still adds substantial behavior: which keys come back ('vimrc', 'warnings', 'ignoreProjectVimrc', 'canEdit'), the shape of each warning ({line, kind, word, message}), and the crucial non-error contract that unrecognized lines are preserved and merely reported as warnings. That last point materially changes how an agent interprets a response that would otherwise look like a failure.

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

Conciseness3/5

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

Purpose and scope are front-loaded, which is good, but the bulk is a dense catalog of supported directives (nu/hls/is/ic/scs/ws, nos, inv, &, map variants, key notations) that belongs more naturally to the set_vimrc definition. For a read tool it is heavy and hard to scan, even if technically accurate.

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?

There is no output schema, and the description compensates by enumerating the returned fields and their conditions. What is left implicit is the concrete envelope (a plain string vs. an object holding those keys) and the exact meaning of 'kind' in a warning; otherwise an agent has enough to call and interpret this correctly.

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 meaning the schema does not: a project vimrc "lies over its members' own" and the full four-layer resolution order, plus the 'ignoreProjectVimrc' flag telling the caller project vimrcs do not apply to them. That layering context is what an agent needs to interpret the returned text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact resource ("the vimrc of the tracker's vi mode") and its two scopes — the caller's own or, with 'projectKey', that project's — so an agent knows precisely what it retrieves. It does not explicitly contrast itself with the sibling set_vimrc, so it stops short of full sibling differentiation.

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 selection criteria for the one parameter (omit it for your own vimrc, supply a key for a project's) and spells out the precedence order applied (vim defaults, person's vimrc, project's vimrc, then ':set'). It also states the access rule ("Anybody who sees the project may read its vimrc"), though it never names set_vimrc as the write alternative or states when not to call it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources