properties_risks_landslideLandslide-risk overlays within 1 km. Read on_property — a returned row
means "found nearby", not "this property is at landslide risk".
Price: 3¢ per call.
| Name | Required | Description | Default |
|---|---|---|---|
| geojson | No | When true, add a `geojson` FeatureCollection of the hazard polygons clipped to a 1km-radius circle around the property, plus `geojson_meta` (default false — response unchanged). | |
| gnaf_id | Yes |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -{
- "properties": {
- "available": {
- "anyOf": [
- {
- "type": "boolean"
- },
- {
- "type": "null"
- }
- ],
- "description": "`false` on no-data responses. Omitted on success — branch on `data !== null` if you want a single discriminator.",
- "title": "Available"
- },
- "data": {
- "anyOf": [
- {
- "items": {
- "additionalProperties": true,
- "description": "One hazard overlay found near the property.\n\n**A record means the hazard exists within 1 km — read `on_property` to\nlearn whether it covers the property itself.** Every overlay is searched\ninside a 1 km circle around the address point, so the presence of a\nrecord on its own says only *there is mapped hazard land in this\nneighbourhood*. Most records are proximity hits: the property is not in\nthe zone. Never render \"a bushfire record came back\" as \"this property\nis bushfire-prone\" — check `on_property` first, and quote\n`nearest_distance_m` when it is false.\n\n`on_property` is tested against the address point (the geocoded location\nof the dwelling), not a surveyed parcel boundary, so a zone whose edge\nruns through the block can read false while still clipping the land. It\nis a strong indication, not a statutory answer: nothing here substitutes\nfor a planning certificate.",
- "example": {
- "area_level": "Layer",
- "area_name": "Risk Layer",
- "features_within_radius": 25,
- "name": "Fire",
- "nearest_distance_m": 0,
- "on_property": true,
- "search_radius_m": 1000,
- "value": "On property"
- },
- "properties": {
- "area_level": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "description": "Constant `'Layer'` on property risks — a placeholder marking these as map-layer hits rather than statistics for a suburb or region. It is not a geographic level and carries no information; the suburb risk endpoints use this slot for a real one.",
- "title": "Area Level"
- },
- "area_name": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "description": "Constant `'Risk Layer'` on property risks. Like `area_level`, a placeholder that keeps the row shape consistent with area-based responses — not the name of any actual area, and not the name of the hazard (that is `name`).",
- "title": "Area Name"
- },
- "features_within_radius": {
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
- ],
- "description": "How many features of this overlay fall inside `search_radius_m`. Separates 'one stray polygon clips the corner of the neighbourhood' from 'the whole area is mapped'. Absent on public-housing records, where each record already is one Census area.",
- "title": "Features Within Radius"
- },
- "geojson": {
- "anyOf": [
- {
- "additionalProperties": true,
- "type": "object"
- },
- {
- "type": "null"
- }
- ],
- "description": "GeoJSON FeatureCollection of the hazard polygons for this overlay, ST_Intersection-clipped to a 1km-radius circle around the property and simplified for browser use. Present only when the request passes `?geojson=true`; absent (and the response byte-identical to before) otherwise.",
- "title": "Geojson"
- },
- "geojson_meta": {
- "anyOf": [
- {
- "additionalProperties": true,
- "type": "object"
- },
- {
- "type": "null"
- }
- ],
- "description": "Clip / simplify / truncation metadata for `geojson` (clip_method='1km_radius', radius_m, simplify tolerance, coordinate precision, feature/byte caps, and whether the size cap truncated the output). Present only with `?geojson=true`.",
- "title": "Geojson Meta"
- },
- "name": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "description": "Which hazard this record is about — a fixed label per overlay, e.g. 'Fire', 'Flood', 'Historically Flooded', 'Landslide', 'Erosion', 'Heritage', 'Environment', 'HV Power Line', 'Mobile Black Spot', 'Public Housing'. Suitable for display as-is.",
- "title": "Name"
- },
- "nearest_distance_m": {
- "anyOf": [
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "Metres from the property's address point to the nearest feature of this overlay, measured geodesically and reported to the whole metre. `0.0` exactly when `on_property` is true. When `on_property` is false this is how far away the hazard really is — a heritage record at 174 m and one at 950 m are both 'found', and only this field separates them. On public-housing records it is the distance to that record's Census area. Accurate to about 2% and biased very slightly long (it never under-reports the gap); at close range the error is sub-metre.",
- "title": "Nearest Distance M"
- },
- "on_property": {
- "anyOf": [
- {
- "type": "boolean"
- },
- {
- "type": "null"
- }
- ],
- "description": "**Whether the hazard actually covers this property**, as opposed to merely existing nearby. True when a feature of this overlay contains the property's address point. This is the field to gate any 'this property is in a flood/bushfire/heritage zone' statement on — record presence alone only means 'found within `search_radius_m`'.\n\nTwo overlays are line/point data rather than zones — HV power lines (`'HV Power Line'`) and mobile black spots (`'Mobile Black Spot'`) — and for those `on_property` is false for every property by construction; `nearest_distance_m` is the signal there. On public-housing records it marks the one Census area the property actually sits in.",
- "title": "On Property"
- },
- "search_radius_m": {
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
- ],
- "description": "The radius searched around the property, in metres (1000). Any record you receive was found inside this circle; anything beyond it was not looked for. Present so the presence rule is explicit rather than folklore.",
- "title": "Search Radius M"
- },
- "value": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "number"
- },
- {
- "type": "null"
- }
- ],
- "description": "A display string summarising this record. On hazard overlays (fire, flood, landslide, erosion, heritage, environment, power lines, black spots) it states the containment result in words — `'On property'`, or `'Not on property; nearest 174 m away'`. It is prose for humans: parse `on_property` and `nearest_distance_m` instead. On public-housing records it is instead a preformatted percentage such as `'3.4%'` (see `value_unit`). Do not parse it as a number without checking `value_unit` first.",
- "title": "Value"
- },
- "value_unit": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "description": "What `value` is measured in, and the flag for whether it is a number at all. Null on hazard overlays, whose `value` is the containment sentence. `'Properties Proportion'` on public-housing records, meaning `value` is the share of dwellings in a nearby small Census area that are public housing, written as a percentage string. Public housing can return several records — one per nearby Census area that clears a minimum share — so expect a list, not a single figure.",
- "title": "Value Unit"
- }
- },
- "title": "RiskRecord",
- "type": "object"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
- ],
- "description": "The endpoint's payload, or `null` when Microburbs has no value.",
- "title": "Data"
- },
- "message": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "description": "Human-readable explanation. Omitted on success.",
- "title": "Message"
- },
- "reason": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "description": "Machine-readable slug naming the no-data condition (e.g. `no_avm_for_GANSW704074813`). Stable per endpoint. Omitted on success.",
- "title": "Reason"
- }
- },
- "title": "ApiResponse[list[RiskRecord]]",
- "type": "object",
- "x-fastmcp-top-level-schema": "ApiResponse_list_RiskRecord__"
-}New value: +nullDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds the important behavioral nuance about the meaning of returned rows and the price per call, which are not covered by annotations. This exceeds the baseline for a read-only tool.
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?
The description is two sentences plus a price note, with the core purpose and interpretation warning front-loaded. Every sentence adds value and there is no fluff. It is an excellent model of concise, high-signal writing.
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 tool with two parameters and no output schema, the description covers the essential meaning and interpretation. It omits details about the geojson parameter's output format, but that is documented in the schema. The absence of an explicit usage-vs-alternatives note is a minor gap, so a 4 is appropriate.
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?
Schema coverage is only 50% (geojson described, gnaf_id not). The description does not mention or elaborate on any input parameters, leaving gnaf_id unexplained. With half the parameters undocumented in the schema and no guidance in the description, the agent lacks semantic understanding of the required identifier.
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 the tool provides landslide-risk overlays within a 1 km radius and explicitly distinguishes the meaning of a returned row ('found nearby') from an actual property risk. This is a specific verb-resource pairing and directly addresses the most common misinterpretation, making it stand out from sibling risk tools.
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?
It provides crucial context on how to interpret results (a row means nearby, not at risk) and the 1 km scope. However, it does not explicitly advise when to choose this tool over alternatives like properties_risks_all or other risk-specific tools; that is left to the name and sibling context.
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.