Aeronaves de um tipo ICAO especifico transmitindo agora no mundo (ex.: PC12 = Pilatus PC-12, E195 = Embraer 195, AS50 = Esquilo). Retorna { total_airborne, aircraft[] } com posição de cada uma. Funciona melhor com tipos menos comuns (até algumas centenas no ar); pra tipos muito comuns (A320, B738, milhares no ar) prefira flightradar_nearby numa região e filtre por type.
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | ||
| limit | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds real behavioral context: it only sees currently transmitting aircraft globally, returns a specific object shape, and has practical scale limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three dense, front-loaded sentences with no filler or repeated title. Each sentence contributes meaning: what the tool returns, output format, and usage guidance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only lookup with no output schema, the description provides return shape, behavior, and a related alternative. The only real gap is not describing the optional `limit` parameter, which makes it slightly incomplete but not ambiguous.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds useful semantics for the `type` parameter by explaining ICAO format and providing examples. However, the `limit` parameter is not explained at all, and schema description coverage is 0%, so the tool description only partially compensates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states what the tool does: it returns aircraft of a specific ICAO type currently transmitting, along with their positions. It also distinguishes itself from sibling tools like flightradar_nearby, which is a region-based alternative.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when the tool works best (less common ICAO types) and when to avoid it, recommending flightradar_nearby as an alternative for common types like A320 and B738. This is concrete, actionable usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The flightradar_* tools are clearly distinct from each other, but the server mixes them with generic platform tools (authenticate, connect, marketplace, toolkit_info) that serve different purposes and some overlap (connect vs. authenticate; marketplace vs. toolkit_info). This creates ambiguity about what the server is actually for.
There is a clear pattern for flightradar_* tools (prefix + resource), but the rest are named inconsistently: simple verbs (authenticate, connect), nouns (marketplace), and verb_noun (report_bug, show_version). No single naming convention is applied across the whole set.
Twelve tools is a reasonable number, but the count is inflated by six unrelated platform management tools that don't belong in a flight radar server. The set feels over-scoped for its stated name and under-scoped for a general MCP platform.
The flightradar_* tools cover core needs: aircraft lookup, airport info, nearby traffic, closest aircraft, military and type filters. Minor gaps exist (e.g., no flight tracks or scheduled arrivals), but the domain is well covered. The platform tools are irrelevant to flight radar but complete in themselves.