Skip to main content
Glama

Building cost per square metre

pricepaid_construction_costs
Read-onlyIdempotent

Use this when a user asks what it costs to build a home or other building per square metre in Brazil (country BR), how much of that is materials and how much is labour, or how states or regions compare. Returns the official average cost per square metre for the latest month published, split into materials and labour, with the previous month, the official source and licence. This is a published survey average of unit costs (price_type official_statistic), not a range built from invoices or sales, so the range fields are null and there is no sample size. How fresh: monthly; the latest month on 16 Oct 2026 was September 2026. Do not use for the price of a finished home, for a builder's quote, for renovation work, or for countries that are not listed.

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": {
      "country": "<country>"
    },
    "name": "pricepaid_construction_costs"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNoState or region, where the publisher splits by place (the country notes say how). Leave out for the national figure. BR: state name or two-letter code ('São Paulo', 'SP', 'Bahia', 'RJ'); leave out for the national figure (Brasil). States:…
countryYesBR = Brazil (all 27 states plus the national figure; IBGE SINAPI average cost per m2)
componentNoWhich part of the cost: total (default), material (building materials) or labour (wages). BR: total (default) = average cost per m2; material = materials part; labour = labour part. All in BRL per m2, monthly.

Output Schema

NameRequiredDescriptionDefault
priceNo
periodNo
sourceNo
statusYes
summaryYesOne sentence an AI can quote.
confidenceNohigh, medium, low or insufficient.
sample_sizeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed33 schema fields changed
    • changedInput schema / properties / area / description
      Previous value: -"State or region, where the publisher splits by place (the country notes say how). Leave out for the national figure. BR: state name or two-letter code ('São Paulo', 'SP', 'Bahia', 'RJ'); leave out for the national figure (Brasil). States: RO = Rondônia, AC = Acre, AM = Amazonas, RR = Roraima, PA = Pará, AP = Amapá, TO = Tocantins, MA = Maranhão, PI = Piauí, CE = Ceará, RN = Rio Grande do Norte, PB = Paraíba, PE = Pernambuco, AL = Alagoas, SE = Sergipe, BA = Bahia, MG = Minas Gerais, ES = Espírito Santo, RJ = Rio de Janeiro, SP = São Paulo, PR = Paraná, SC = Santa Catarina, RS = Rio Grande do Sul, MS = Mato Grosso do Sul, MT = Mato Grosso, GO = Goiás, DF = Distrito Federal."New value: +"State or region, where the publisher splits by place (the country notes say how). Leave out for the national figure. BR: state name or two-letter code ('São Paulo', 'SP', 'Bahia', 'RJ'); leave out for the national figure (Brasil). States:…"
    • changedOutput schema / description
      Previous value: -"A price answer: a range or an official statistic with sample size, period, confidence, source and licence."New value: +"Price range from real records: price, sample_size, period, confidence, source and licence."
    • removedOutput schema / properties / answer_id
      Removed value: -{
      -  "description": "Audit trail: a stable id (hash of source id, normalised query, data period and method_version). The same question on the same data gives the same id; keep it with the reasoning that used the figure.",
      -  "type": "string"
      -}
    • removedOutput schema / properties / as_of
      Removed value: -{
      -  "description": "When the answer was produced (ISO 8601); the snapshot date when the official source was down and the answer comes from our copy.",
      -  "type": "string"
      -}
    • changedOutput schema / properties / confidence / description
      Previous value: -"high = 50+ records, medium = 15–49, low = 5–14."New value: +"high, medium, low or insufficient."
    • removedOutput schema / properties / confidence / enum
      Removed value: -[
      -  "high",
      -  "medium",
      -  "low",
      -  "insufficient"
      -]
    • removedOutput schema / properties / data_age_days
      Removed value: -{
      -  "description": "Whole days between data_as_of and retrieved_at; null when data_as_of is null.",
      -  "type": [
      -    "number",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / data_as_of
      Removed value: -{
      -  "description": "ISO date (YYYY-MM-DD) of the newest data point behind the figure; null when unknown.",
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / evidence
      Removed value: -{
      -  "additionalProperties": {},
      -  "description": "Audit trail: what kind of evidence the figure is.",
      -  "properties": {
      -    "label": {
      -      "description": "Short name of the kind of evidence, e.g. 'Recorded sale prices', 'Official published average', 'Official published index', 'Posted shelf or pump price', 'Posted or listed price', 'Contract award value', 'Regulated reimbursement price'.",
      -      "type": "string"
      -    },
      -    "meaning": {
      -      "description": "One sentence on what this kind of evidence does and does not establish.",
      -      "type": "string"
      -    },
      -    "type": {
      -      "description": "Same as price_type.",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "type",
      -    "label",
      -    "meaning"
      -  ],
      -  "type": "object"
      -}
    • removedOutput schema / properties / extra
      Removed value: -{
      -  "additionalProperties": {},
      -  "description": "Source-specific details (for example cheapest stations). extra.stale is true when the answer comes from our copy of the source.",
      -  "propertyNames": {
      -    "type": "string"
      -  },
      -  "type": "object"
      -}
    • removedOutput schema / properties / method
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / method_url
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / method_version
      Removed value: -{
      -  "description": "Audit trail: version of the way this source turns raw data into an answer (per source, default '1').",
      -  "type": "string"
      -}
    • removedOutput schema / properties / notice
      Removed value: -{
      -  "description": "Information, not a valuation or offer. Also says when the answer is our copy because the official source did not respond.",
      -  "type": "string"
      -}
    • removedOutput schema / properties / period / description
      Removed value: -"The period the records cover (ISO dates), or the date of the snapshot when the answer comes from our copy."
    • changedOutput schema / properties / price / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": {},
      -    "description": "The price. Null when there is not enough data to publish a figure (fewer than 5 records) or nothing matched.",
      -    "properties": {
      -      "currency": {
      -        "description": "ISO 4217 currency code, e.g. EUR.",
      -        "type": "string"
      -      },
      -      "max": {
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "measure": {
      -        "description": "What value is: median for ranges built from records; average or median for official statistics.",
      -        "enum": [
      -          "median",
      -          "average"
      -        ],
      -        "type": "string"
      -      },
      -      "median": {
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "min": {
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "typical_high": {
      -        "description": "90th percentile; null for official statistics that give no range.",
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "typical_low": {
      -        "description": "10th percentile; null for official statistics that give no range.",
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "unit": {
      -        "description": "What the price is per, e.g. 'per litre', 'per home', 'per kWh'.",
      -        "type": "string"
      -      },
      -      "value": {
      -        "description": "The headline figure. For ranges built from records it equals median.",
      -        "type": "number"
      -      }
      -    },
      -    "required": [
      -      "currency",
      -      "unit",
      -      "value"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {},
      +    "properties": {
      +      "currency": {
      +        "type": "string"
      +      },
      +      "typical_high": {
      +        "type": [
      +          "number",
      +          "null"
      +        ]
      +      },
      +      "typical_low": {
      +        "type": [
      +          "number",
      +          "null"
      +        ]
      +      },
      +      "unit": {
      +        "type": "string"
      +      },
      +      "value": {
      +        "type": "number"
      +      }
      +    },
      +    "required": [
      +      "currency",
      +      "unit",
      +      "value"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / price_type
      Removed value: -{
      -  "description": "transaction, posted_pump_price, posted_price, contract_price, reimbursement_price or official_statistic.",
      -  "type": "string"
      -}
    • removedOutput schema / properties / query
      Removed value: -{
      -  "additionalProperties": {},
      -  "description": "The request as understood, echoed back.",
      -  "propertyNames": {
      -    "type": "string"
      -  },
      -  "type": "object"
      -}
    • removedOutput schema / properties / reliability
      Removed value: -{
      -  "description": "How far to trust the figure as a distribution of real prices. official_with_count = a published official figure with a record count; official_median_no_count = a published average or median with no record count (confidence 'high' there means the publisher is official, not that a count was checked); record_level = 15+ records we hold; thin = 5–14 records; stale = our copy because the official source did not respond; insufficient_data = no figure published.",
      -  "enum": [
      -    "official_with_count",
      -    "official_median_no_count",
      -    "record_level",
      -    "thin",
      -    "stale",
      -    "insufficient_data"
      -  ],
      -  "type": "string"
      -}
    • removedOutput schema / properties / retrieved_at
      Removed value: -{
      -  "description": "Audit trail: when ProofPrice produced this answer (ISO 8601). For an answer from our own copy this is now, while as_of is the snapshot date.",
      -  "type": "string"
      -}
    • removedOutput schema / properties / sample_size / description
      Removed value: -"Number of records behind the figure; null when the publisher does not say."
    • removedOutput schema / properties / source / description
      Removed value: -"Where the figure comes from, under which licence, and the attribution line to show."
    • removedOutput schema / properties / source / properties / attribution / description
      Removed value: -"The attribution line to show with the figure."
    • removedOutput schema / properties / source / properties / id
      Removed value: -{
      -  "description": "Source id, e.g. es-fuel.",
      -  "type": "string"
      -}
    • removedOutput schema / properties / source / properties / licence_url
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / source / properties / publisher
      Removed value: -{
      -  "description": "Who publishes the data.",
      -  "type": "string"
      -}
    • removedOutput schema / properties / source / properties / url
      Removed value: -{
      -  "description": "The publisher's page for this data.",
      -  "type": "string"
      -}
    • changedOutput schema / properties / source / required
      Previous value: -[
      -  "id",
      -  "name",
      -  "publisher",
      -  "licence",
      -  "licence_url",
      -  "attribution",
      -  "url"
      -]New value: +[
      +  "name",
      +  "licence",
      +  "attribution"
      +]
    • removedOutput schema / properties / statistic
      Removed value: -{
      -  "additionalProperties": {},
      -  "description": "Official statistics only: what kind of figure it is and the period the publisher states it for.",
      -  "properties": {
      -    "measure": {
      -      "enum": [
      -        "median",
      -        "average"
      -      ],
      -      "type": "string"
      -    },
      -    "note": {
      -      "type": "string"
      -    },
      -    "reference_period": {
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "measure",
      -    "reference_period"
      -  ],
      -  "type": "object"
      -}
    • removedOutput schema / properties / status / description
      Removed value: -"ok = a figure is returned; insufficient_data = fewer than 5 matching records; no_matches = nothing matched."
    • removedOutput schema / properties / suggestions
      Removed value: -{
      -  "description": "Short plain things to try next: widen the period or area, ask for an itemised quote. May be empty.",
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • changedOutput schema / properties / summary / description
      Previous value: -"One plain sentence an AI can quote."New value: +"One sentence an AI can quote."
    • changedOutput schema / required
      Previous value: -[
      -  "query",
      -  "status",
      -  "source",
      -  "summary",
      -  "notice"
      -]New value: +[
      +  "status",
      +  "summary"
      +]
  2. Changed1 schema field changed
    • changedOutput schema / properties / evidence / properties / label / description
      Previous value: -"Short name of the kind of evidence, e.g. 'Recorded sale prices', 'Official published average', 'Posted shelf or pump price', 'Contract award value', 'Regulated reimbursement price'."New value: +"Short name of the kind of evidence, e.g. 'Recorded sale prices', 'Official published average', 'Official published index', 'Posted shelf or pump price', 'Posted or listed price', 'Contract award value', 'Regulated reimbursement price'."
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), but the description adds substantial beyond-schema context: the data is a published survey average (price_type official_statistic rather than invoice-derived), the range fields will be null, there is no sample size, it returns the previous month alongside the latest, and it names the source and licence. It goes further with a concrete freshness anchor ('the latest month on 16 Oct 2026 was September 2026'), which tells the agent exactly how stale a result may be — a rare and valuable disclosure.

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?

Structure is strong: use-case first, then return shape, then data provenance, then freshness, then exclusions. Most sentences carry distinct information, though the caveat about ranges and sample size and the price_type parenthetical verge on restating the same point about survey averages.

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?

For a read-only lookup with an output schema, annotations and full param coverage, everything an agent needs is present: what it returns, the time granularity, the data vintage, the unit (BRL per m2), and what the tool is not for. Nothing material is left to inference.

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% and both enums are documented in the schema itself, so the baseline of 3 applies. The description restates the materials/labour split and the national-vs-state default in prose, which reinforces but does not extend the per-parameter documentation.

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 opening sentence names a specific verb and resource ('what it costs to build a home or other building per square metre in Brazil') and immediately discloses the materials/labour split and state comparison angle. It also explicitly demarcates itself from the nearest lookalikes — finished-home prices, builder quotes, renovation — so an agent can route correctly 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is stated on both sides: 'Use this when a user asks...' followed by an explicit exclusion list ('Do not use for the price of a finished home, for a builder's quote, for renovation work, or for countries that are not listed'). The only mild gap is that exclusions are given as categories rather than sibling tool names, but the boundaries are unmistakable.

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.