Skip to main content
Glama

focus_area

Load a region by circle or polygon and return a fresh intelligence bundle covering aircraft, vessels, GPS jamming, and fused anomalies with a threat level for situational assessment.

Instructions

Load a region PRIMARY and return a full intel bundle for it in one call.

This is the headline tool. It triggers a DEDICATED, always-fresh fetch for just this area (bypassing global rate limits) and registers it for ongoing priority refresh. The bundle contains: fresh aircraft summary + sample, aircraft-density grid, GPS-jamming assessment, vessels, and fused anomalies (emergencies, jamming hotspots, dark vessels, alerts) with a threat level.

Args: lat, lon: centre of the area of interest. Required unless polygon is given, in which case they are ignored. radius_nm: radius in nautical miles (1–250; default 200). label: optional human name for the AOI (e.g. "Kaliningrad"). cell_deg: density grid cell size in degrees (0.1–10; default 1.0). polygon: optional irregular region as ONE ring of [lon, lat] pairs (longitude FIRST; 3–500 vertices, closed or open; no holes, no antimeridian crossing). Overrides lat/lon/radius_nm: its bounding circle (max 250 nm, else polygon_truncated) is loaded PRIMARY and every record outside the ring is dropped. Grid cells and jamming hexes are kept by centre point, so use a small cell_deg for a small ring. A total the capped samples cannot give for the ring comes back as _in_circle (the bounding circle's figure).

Input Schema

NameRequiredDescriptionDefault
latNo
lonNo
labelNo
detailNoshort
polygonNo
cell_degNo
radius_nmNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does well: it discloses the dedicated fetch bypassing global rate limits, ongoing priority refresh registration, and threat-level output. It omits cost/latency expectations and any permission requirements, which keeps it from a 5.

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

Conciseness4/5

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

Front-loaded with the core action and bundle contents, then structured Args. The polygon paragraph is dense but every clause (antimeridian, holes, cell sizing, _in_circle totals) prevents a real misuse, so it earns its space.

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 return values needn't be re-explained, and the description still usefully names the bundle components. The only substantive gap is the undocumented 'detail' parameter and no guidance on result size/pagination behavior.

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 0%, so the description must compensate, and it does for lat/lon, radius_nm, label, cell_deg and especially polygon (lon-first ordering, 3–500 vertices, bounding-circle truncation, centre-point grid attribution). The 'detail' parameter is never mentioned, leaving one of seven params undocumented.

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 and resource ('Load a region PRIMARY and return a full intel bundle') plus the exact bundle contents, which clearly separates it from single-signal siblings like query_aircraft or gps_jamming. The 'primary area of interest' framing is unambiguous.

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?

Calls itself 'the headline tool' and explains the dedicated always-fresh fetch with priority refresh, which tells the agent this is the primary entry point. It does not explicitly name alternatives (get_situation, intel_brief, area_baseline) or state when NOT to use it, so it stops short of a 5.

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