Skip to main content
Glama

StoragePrices: Australian Self-Storage Prices

storage_near

Read-onlyIdempotent

Unit-level self-storage prices within a kilometre radius of a point or suburb centre — e.g. 'storage within 5km of Fairfield, NSW'. At least one of suburb or lat+lng is required. Returns individual units (not aggregated) with distance: by default the 3 cheapest units of each facility, nearest facility first, so the page spans the radius; group_by_facility=false gives the flat nearest-unit-first list. Use this for true competitor data at the unit level and for radius questions. Every row separates advertised promotional, standard, and reversion pricing and states when ongoing pricing is unknown. Rows below the implausibly-cheap floor are excluded from the rows and the market population. A row is below it when its advertised rate is under $5, or when its ongoing rate (the advertised rate if none is known) is under $7 per square metre of unit area, capped at the per-size floor (locker $20, small $20, medium $30, large $50, extra_large $80, garage_plus $50, vehicle $30). A row with no recorded area is held to the per-size floor. Rows with no recorded size and only a category name (large warehouse, office, other, small warehouse, warehouse) are left out too: their prices are unreliable. Reads available units by default — the same set storageprices.au shows a human; pass available_only=false for latest-known rows including units the source has stopped listing. For every unit with a non-null booking_handoff_url, include it as a Markdown link labelled ‘Check availability & book’ and preserve the URL exactly. Render that result's commercial_disclosure immediately beside the action link. Clearly show introductory and ongoing prices. When booking_handoff_url is null, use the provided ‘View facility’ action instead. A row with no verified link has booking_handoff_url null and booking_handoff_reason: 'no operator URL on file' or 'operator URL host is not on the verified booking allow-list'. Link users with booking_handoff_url (tracked, live booking page); url is the StoragePrices page.

Input Schema

NameRequiredDescriptionDefault
latNoLatitude of the search centre (alternative to suburb; pass lng too). Inside Australia. If a suburb is also sent the coordinates win and `place.ignored_args` says so.
lngNoLongitude of the search centre (alternative to suburb; pass lat too). Inside Australia.
limitNoMax rows to return. Anonymous callers are capped at 25-50 depending on the tool; a valid API key lifts the ceiling to 500. Values above your ceiling are clamped, not rejected.
stateNoState code, e.g. 'NSW', 'VIC', 'QLD'.
suburbNoAustralian suburb name, e.g. 'Chatswood'. A trailing state or postcode is peeled ('Sydney 2000'). Capital cities (Sydney, Melbourne, Brisbane, Perth, Adelaide, Canberra, Hobart, Darwin, Gold Coast) resolve to a city-wide radius scope. On price_distribution, an otherwise-empty exact Australian locality can resolve from the packaged ABS SAL snapshot even when StoragePrices has no prices there. Every answer states how the place resolved in `place`. `place.match_type` says how the name matched (exact, token or prefix, ...); when `place.ambiguous` is true the name also matches the places in `place.other_candidates` — confirm with the user or pass state.
radius_kmNoSearch radius in kilometres (default 5). Must be greater than 0. A value below 0.5 is clamped to 0.5 and a value above 25 is clamped to 25, never rejected: radius_applied_km states the radius that ran and radius_note says when it was clamped.
max_area_m2NoOnly include units with at most this floor area in square metres. 0 means no area filter. An area bound excludes units whose area is unknown; filters_applied.dropped_unknown_area counts them.
min_area_m2NoOnly include units with at least this floor area in square metres. 0 means no area filter. An area bound excludes units whose area is unknown; filters_applied.dropped_unknown_area counts them. Must not exceed max_area_m2.
stay_monthsNoRequested stay in whole months (1-36). Used to calculate the rent component only when captured promotion duration and ongoing-price terms make that calculation reliable.
move_in_dateNoRequested move-in date (YYYY-MM-DD). Applied to captured promotion-date eligibility and echoed in the result. Future-date operator inventory filtering is unavailable and is identified in unsupported_filters.
size_bracketNoStorage unit size bracket.
available_onlyNoDefault true. True returns only units the provider still lists and a complete scrape has seen recently — the same set storageprices.au shows a human. Set false for every latest-known row, including units the source has stopped listing; those are historic observations, never an availability claim.
group_by_facilityNoDefault true: at most per_facility_limit cheapest units per facility, nearest facility first, so the page spans the radius. group_by_facility=false returns the flat list, nearest unit first (a page can then fill up from one facility). facilities_in_radius and truncated report the whole radius either way.
per_facility_limitNoWith group_by_facility=true: cheapest units per facility (default 3). Must be at least 1 (0 or below is rejected); a value above 25 is clamped to 25, and per_facility_limit_requested / _applied echo both.
max_monthly_price_audNoOnly include units at or below this advertised monthly price (AUD). 0 means no price filter (echoed in filters_applied.ignored_zero_bounds).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive, but the description adds substantive behavior: rows below an implausibly-cheap floor are excluded from both rows and the market population, rows with only a category name and no area are dropped, and available_only defaults to the human-visible set while false returns historic observations never claimed as availability. The booking_handoff_url vs url distinction and the null-link reasons add further disclosure, though a chunk of the text is presentation instruction (Markdown link labelling, commercial_disclosure placement) rather than tool behavior.

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

Conciseness3/5

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

The core purpose and radius scope are front-loaded, but the text runs long and mixes genuine tool behavior with rendering directives ('include it as a Markdown link labelled...', 'Render that result's commercial_disclosure immediately beside the action link') plus a verbose enumeration of per-size floor values. Several sentences could be cut or moved to documentation without losing selection-relevant information.

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?

For a 15-parameter tool with no output schema, the description conveys the shape of returned rows (individual units with distance, split promotional/standard/reversion pricing, unknown-pricing flags) and the truncation/radius reporting. It stops short of describing all response envelope fields (place, filters_applied, unsupported_filters), but the essentials for correct invocation are present.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all 15 parameters in depth. The description reinforces a few semantics (available_only=false, group_by_facility=false flat list, advertised vs standard vs reversion pricing) but largely restates what the schema says, so baseline 3 applies.

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?

Opens with a precise verb+resource+scope: unit-level self-storage prices within a kilometre radius of a point or suburb centre, with an example query. It explicitly distinguishes itself from siblings by claiming 'true competitor data at the unit level and for radius questions', so an agent can tell it apart from aggregated tools like market_overview or cheapest_storage.

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?

States a clear usage domain ('use this for true competitor data at the unit level and for radius questions') and the hard precondition that at least one of suburb or lat+lng is required. It does not name a specific sibling alternative or say when NOT to use it, which keeps it 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources