Skip to main content
Glama

ourairports-mcp-server

ourairports_search_runways
Read-onlyIdempotent

Search runways across the whole bundled OurAirports corpus by attribute, joined back to their airports — the cross-airport counterpart to ourairports_get_airport (which returns runways for one already-known airport). Filter by airport facets (country, region, type) and runway facets (surface, min_length_ft, min_width_ft, lighted). Returns one flat {airport, runway} row per matching runway, so an airport with three matching runways contributes three rows. surface is a case-insensitive substring match against the raw upstream surface string, not an exact code — the runway surface must CONTAIN your text, so a shorter fragment matches more variants (no controlled vocabulary: "asp" matches ASP, ASPH, and Asphalt). A runway whose length or width is unknown is excluded when the matching min_*ft filter is set — the data can never confirm it meets the threshold. Closed airports and closed runways are both excluded unless their include* flag is set. Use ourairports_list_countries for valid country/region codes. OurAirports is community-edited — not authoritative for flight operations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNoRestrict to runways at airports of one type: large_airport, medium_airport, small_airport, heliport, seaplane_base, balloonport, or closed.
limitNoMaximum runway rows to return (1–100). Defaults to OURAIRPORTS_DEFAULT_SEARCH_LIMIT (20).
regionNoISO 3166-2 region code filter (e.g. US-WA). Exact match, case-insensitive; surrounding whitespace is ignored.
countryNoISO 3166-1 alpha-2 country code filter (e.g. US). Exact match, case-insensitive; surrounding whitespace is ignored. Discover codes with ourairports_list_countries.
lightedNoFilter by runway lighting: true for lighted runways only, false for unlighted only. Omit to include both.
surfaceNoSurface filter — case-insensitive substring match against the raw upstream surface string (free text, no controlled vocabulary; ~654 distinct values). Match the literal text as recorded: "asp" matches ASP/ASPH/Asphalt/ASPH-G, "con" matches CON/Concrete, "turf" or "grs" for grass strips. A shorter fragment matches more variants; there is no enum or reference tool for surfaces.
min_width_ftNoMinimum runway width in feet (inclusive). Runways with an unknown width are excluded when this is set, never assumed to pass.
min_length_ftNoMinimum runway length in feet (inclusive). Runways with an unknown length are excluded when this is set, never assumed to pass.
include_closed_runwaysNoInclude runways flagged closed. Off by default.
include_closed_airportsNoInclude runways at airports of type "closed". Off by default.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
capNoThe limit that was applied. Present only when results were truncated.
errorNoPresent when the call failed. Absent on success.
shownNoNumber of runway rows returned. Present only when results were truncated.
noticeNoGuidance when nothing matched or results were capped — how to broaden or narrow.
runwaysNoMatching runways, each paired with its airport. One row per runway — an airport with N matching runways contributes N rows.
truncatedNoPresent and true only when more runways matched than were returned.
totalCountNoTotal matching runways before the limit was applied.

TDQS

A5/5.0
Behavior5/5

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

Discloses behaviors beyond the readOnly/idempotent annotations: flat row structure (one row per matching runway), surface substring matching semantics with examples, exclusion of runways with unknown length/width when min_*_ft filters are set, and closed handling. These are non-obvious traits essential for correct invocation and interpretation.

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?

Despite its length, every sentence adds distinct value: purpose, sibling contrast, output shape, surface semantics, unknown-value handling, closed handling, reference tool, and data quality caveat. Information is front-loaded with the primary purpose and key differentiator first, and the structure is logical.

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?

Given the tool's complexity (10 parameters, 100% schema coverage, output schema present) and annotations, the description covers all critical aspects: return format, filtering edge cases, exclusion rules, reference to country codes, and data quality caveats. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds crucial semantic depth: the surface parameter's substring behavior (no controlled vocabulary, shorter fragments match more), the min_length_ft/min_width_ft exclusion rule, and the include_closed_* flags' effects. This goes well beyond the schema's per-parameter descriptions.

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 (Search) and resource (runways) across the whole bundled corpus, and explicitly contrasts with ourairports_get_airport (which returns runways for one already-known airport). This makes the tool's purpose and scope unambiguous and differentiates it from the sibling tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly frames this tool as the 'cross-airport counterpart' to ourairports_get_airport, telling the agent when to use it instead. Also directs to ourairports_list_countries for valid country/region codes and warns that the data is community-edited, providing clear context for when to trust the results.

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.

TDQS

A4.7/5.0
Disambiguation5/5

Each tool targets a distinct operation: spatial lookup (find_airports, find_navaids), code-based retrieval (get_airport), free-text/faceted search (search_airports), runway attribute search (search_runways), and a reference table (list_countries). No two tools overlap in purpose; even the two 'search' tools are clearly differentiated by entity type.

Naming Consistency5/5

All tool names follow a strict 'ourairports_<verb>_<noun>' pattern with snake_case throughout. Verbs are distinct and indicative (find, get, list, search), and nouns clearly identify the resource (airports, navaids, countries, runways). The pattern is uniform and predictable.

Tool Count5/5

The server exposes exactly 6 tools, which is well-scoped for its domain. Each tool addresses a distinct core need: spatial proximity, code resolution, text/facet search, runway attributes, navaid lookup, and country/region reference. No unnecessary tools, and the count is within the ideal 3-15 range.

Completeness5/5

The surface covers the full read-only lifecycle for aviation data: find by location, resolve by code, search by name/facets, inspect runways, and retrieve navaids. The inclusion of a country lookup table for valid filters and clear cross-references (e.g., search_airports → get_airport) demonstrates thoughtful coverage. Since the dataset is static, CRUD operations aren't expected, and no obvious gaps exist.