Skip to main content
Glama

StoragePrices: Australian Self-Storage Prices

price_trends

Read-onlyIdempotent

Add provider (for example storage_king) for provider history: ongoing and advertised monthly series, typical matched-facility movement and rising/falling counts, with explicit coverage gates. Provider-only queries are allowed and return separate size panels, never an all-size median. Storage King and National reconstruct products from historical booking links; other providers have descriptive history but no supported matched headline. A failed coverage gate returns insufficient_comparable_history, never a fallback price movement. Provider history defaults to monthly full UTC periods; use facility_id for a single facility. Without provider, returns the existing market trend: median advertised monthly price per week or month over a lookback window, plus the promotional share each period. Use for 'are prices going up?', seasonality, and promo cycles. Returns a chart-ready time series. trend_summary.direction follows the like-for-like matched panel (direction_basis) and keeps the raw change as advertised_change_pct. National and state-level series are cached for ten minutes (cached, cache_age_s). A query that overruns its statement timeout returns error_code='timeout' with retryable=true — narrow lookback_days or add state/suburb. Requires at least one of: suburb, state, size_bracket, provider.

Input Schema

NameRequiredDescriptionDefault
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.
providerNoProvider slug or name, e.g. storage_king / Storage King. Enables provider history.
facility_idNoOptional exact facility ID, within provider. Requires provider; any geography also intersects this filter.
granularityNoTime bucket size (default month for provider history, week for market history).
size_bracketNoStorage unit size bracket.
lookback_daysNoHow far back to look, in days (default 180, max 1095). Values outside 7–1095 are clamped; lookback_days_requested / _applied echo both.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior beyond that: coverage gates, the insufficient_comparable_history failure with no fallback movement, which providers support matched headlines (Storage King, National) versus descriptive-only history, ten-minute caching of National/state series with cache_age_s, and timeout error_code with retryable=true. These are exactly the operational traits an agent needs before calling.

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?

It is front-loaded with the provider mode first and then the default market mode, and nearly every sentence carries behavioral information. It is dense and somewhat run-on in places (e.g., the matched-facility movement clause), but there is little outright filler.

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 7-parameter tool with no output schema, the description explains the return shape well: chart-ready time series, separate size panels for provider-only queries, trend_summary.direction with direction_basis and advertised_change_pct, plus cached/cache_age_s fields. The exact contents of a 'size panel' are left implicit, which is the only notable gap.

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 description coverage is 100%, so the schema already documents state, suburb, provider, facility_id, granularity, size_bracket and lookback_days in detail, including the mode-dependent granularity defaults. The description adds little parameter-level meaning beyond restating provider examples and the facility_id single-facility case, so baseline 3 is appropriate.

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?

The description states a specific verb+resource (returns price trends / provider history) and explicitly splits the two modes: with provider it returns ongoing and advertised monthly series plus matched-facility movement; without provider it returns the market median advertised monthly price per period with promotional share. This is enough for an agent to tell it apart from price_distribution or compare_prices without opening the schema.

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?

It gives concrete use cases ('are prices going up?', seasonality, promo cycles), states that provider-only queries are allowed, tells the agent to use facility_id for a single facility, and gives remediation for timeouts (narrow lookback_days or add state/suburb). What it lacks is an explicit routing statement against named siblings (e.g., when to prefer price_distribution or compare_prices instead).

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