Skip to main content
Glama

StoragePrices: Australian Self-Storage Prices

operator_benchmark

Read-onlyIdempotent

For SELF-STORAGE OPERATORS checking their OWN pricing. Give your advertised monthly rate and a market; returns whether you're below / above / aligned with the local median per unit size, the %-distance, the annualised $ per unit you're leaving on the table (or charging over), and your rank vs nearby competitors. Omit size_bracket to sweep all unit sizes at once. Use for 'am I underpriced / overpriced / leaving money on the table / can I raise my rates'. Advertised public rates only — not occupancy or RevPAM. A market needs 3 competitor facilities and 3 observations; below that the status is insufficient_data. Omit my_monthly_price_aud if the user has not stated a price. Never invent one. Without a price the answer is the market median per unit size with verdict=null and a next_step. Pass provider or facility (the operator's own brand) so their own units are excluded from the competitor set. 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.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "suburb": "<suburb>",
      "state": "<state>"
    },
    "name": "operator_benchmark"
  }
}

Input Schema

NameRequiredDescriptionDefault
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.
stateYesState code, e.g. 'NSW', 'VIC', 'QLD'.
suburbYesAustralian 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.
facilityNoYour facility name, if focusing the comparison.
providerNoProvider slug to exclude/identify your own brand.
size_bracketNoUnit size to benchmark. Omit to benchmark all sizes at once.
my_monthly_price_audNoThe operator's own advertised monthly price (AUD) to benchmark, greater than 0. Optional: omit it when the user has not stated a price.
my_ongoing_price_audNoKnown post-promotion ongoing monthly rate (AUD), if publicly disclosed.
my_price_is_promotionalNoTrue when my_monthly_price_aud is an introductory/promotional rate. When omitted the price is treated as ongoing and the answer says assumed_ongoing=true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Far beyond the readOnly/idempotent annotations: it discloses the data-sufficiency rule (3 facilities and 3 observations, else status insufficient_data), the degradation path when no price is supplied (verdict=null plus a next_step), and the self-exclusion mechanism via provider/facility. The floor-exclusion rules for implausibly cheap rows and un-sized rows explain exactly which rows vanish from the result set — behavior an agent could not infer from the schema.

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?

Purpose and usage are well front-loaded in the first sentences, but the final third is a dense wall of floor-threshold detail (dollar and per-square-metre cutoffs for seven size categories) that reads like implementation logic rather than decision-relevant guidance for tool selection. It is informative but disproportionately long relative to the rest.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description enumerates the returned fields and their meaning (status below/above/aligned, %-distance, annualised $, rank, verdict=null with next_step, insufficient_data). Combined with the exclusion rules and the no-price fallback, an agent has everything needed to call this correctly and interpret the result.

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 already 100%, so the baseline is 3; the description earns above that by explaining intent-level semantics: size_bracket omitted means sweep all sizes, my_monthly_price_aud omitted means fall back to median-with-no-verdict, and provider/facility exist specifically to exclude the operator's own units. The explanation of the implausibly-cheap floor also clarifies how those inputs alter the computed population.

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 specific actor and action: 'For SELF-STORAGE OPERATORS checking their OWN pricing', then names the exact output — median comparison per unit size, %-distance, annualised $ gap, and rank vs nearby competitors. This is a distinct benchmark tool, clearly separable from price-lookup siblings like cheapest_storage or price_distribution.

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?

Gives an explicit trigger phrase set ('am I underpriced / overpriced / leaving money on the table / can I raise my rates') and a clear scope exclusion ('Advertised public rates only — not occupancy or RevPAM'). It also states conditional behaviors (omit size_bracket to sweep all sizes; omit price if the user gave none). It stops short of naming a sibling alternative, so not 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