Skip to main content
Glama

Search L-Vars

msfs_search_lvars
Read-onlyIdempotent

Search aircraft L-vars by keyword, automatically scoping to the current aircraft's catalog. Get paginated results with filters for category, prefix, and writable-only variables.

Instructions

Search known aircraft L-vars by keyword.

Searches the embedded L-var catalog for the current aircraft, or every known aircraft catalog if none is loaded or auto-detected. Results are paginated. Auto-detection tries, in order: PMDG's own client-data-area probe (authoritative -- confirms which SDK the aircraft is actually running, independent of what TITLE/ATC_MODEL say), every catalog's own title_pattern matched against TITLE/ATC_MODEL (the only mechanism for a third-party catalog dropped into data/), then honest absence.

When no aircraft catalog could be auto-detected and 'catalog' was not given, this searches every catalog ('filters.catalog' reads "all") and 'message' explains how to scope the search instead. Otherwise, 'message' still discloses how the catalog was resolved -- a probed detection is a materially stronger signal than a title-text match, and a caller deciding how much to trust the result should be able to tell them apart. When the search was not scoped to one confirmed catalog, the markdown table also carries a 'Catalog' column per row -- with the Fenix catalog removed, every bundled catalog is PMDG, so a table of PMDG variables must not render as if it were confirmed for whatever aircraft is actually loaded.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum results
offsetNoResults to skip, for paging
prefixNoFilter by the catalog's variable-type prefix, matched exactly against each entry's 'prefix' field, e.g. PMDG's 'MCP', 'ELEC', 'EVT'. A catalog you build yourself (see msfs_browse_lvar_catalog) may use a different convention -- browse a panel first if you're unsure what a given catalog uses.
catalogNoExplicit catalog key to search, e.g. 'pmdg_737', 'pmdg_777', overriding auto-detection. Use this when the loaded aircraft isn't auto-detected, or to search a specific aircraft's catalog regardless of what's loaded. Call msfs_browse_lvar_catalog() with no arguments for the full list of keys currently bundled or dropped into data/ locally.
keywordYesSearch term, e.g. 'seatbelt', 'autopilot', 'heading', 'fuel'
categoryNoFilter by panel/system category, e.g. 'Signs', 'FCU', 'Electrical'
writable_onlyNoOnly return variables that can be written to
response_formatNo'markdown' for a compact table, 'json' for rowsmarkdown

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv1.0.1

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the read-only/idempotent annotations, the description discloses pagination, the ordered auto-detection strategy, the authoritative PMDG probe vs title-text match distinction, how 'message' explains resolution, and the conditional 'Catalog' column in markdown output. This is far more behavioral disclosure than annotations provide.

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?

The description is long but tightly structured: purpose first, then scope, pagination, auto-detection, fallback behavior, and trust caveats. Every sentence contributes decision-relevant detail rather than filler, and the front-loaded opening gives immediate orientation.

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?

Combined with a fully described input schema and an output schema, the description covers catalog resolution, trust calibration, pagination, scoping behavior, and result-format caveats. An agent has enough context to select parameters correctly and interpret the response appropriately.

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, and the schema already documents each parameter well. The description adds non-schema meaning by explaining that an unspecified catalog resolves to 'all' when no auto-detection succeeds, and that results are paginated, which enriches the semantics of catalog, limit, and offset.

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 opens with 'Search known aircraft L-vars by keyword' — a specific verb, resource, and search intent. It further clarifies scope ('current aircraft or every known aircraft catalog') which distinguishes it from list and browse siblings without ambiguity.

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?

The description gives clear context on when the search spans all catalogs, and the schema's catalog/prefix parameters point to msfs_browse_lvar_catalog for discovering keys and conventions. However, it does not explicitly contrast this tool against siblings like msfs_list_lvars or msfs_search_simvars, so exclusion conditions are left implicit.

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

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/robin24/simconnect-mcp'

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