Skip to main content
Glama

A house's history

house_history
Read-only

When a covered Vancouver house was built and what stood there: the building permit (1901–1930) and the City's year built, what the 1912 fire insurance map draws on the lot and whether today's building is very likely that one, what stands today, and who lived there in each directory year with each listing's source page (with the people, work and employers the 1920, 1930 and 1940 name sections list at the address), and where the 1911, 1921 and 1931 censuses list households at the address, their people, tenure, rent, rooms, origins and birthplaces (1911 gives only the people, origins and birthplaces; 1931 adds the home's value and a radio) as counts, and in 1921 the people by name as Library and Archives Canada's index gives them, each with its LAC record link. Residents' names through 1945 only; later years show a household and job without names. Anything inferred is marked inferred. A house with more than one answer holds (a hotel or rooming house) answers a summary with every year's count of listings, the latest years in full and each census as its summary; ask again with year for any other directory year or census year.

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": {
      "address": "<address>"
    },
    "name": "house_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoWhich page, when an answer says it has more than one (pages, next_page); 1 if left out.
yearNoOnly this year: a directory year's listings, a census year's (1911, 1921, 1931) households, or both where a year is both. The house's years are in years_listed and residents.
addressYesA Vancouver street address as written today or in the directories ("620 Keefer St", "2649 Yew"), an AddressLore house path ("620-keefer") or its URL.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / page
      Added value: +{
      +  "description": "Which page, when an answer says it has more than one (pages, next_page); 1 if left out.",
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / year
      Added value: +{
      +  "description": "Only this year: a directory year's listings, a census year's (1911, 1921, 1931) households, or both where a year is both. The house's years are in years_listed and residents.",
      +  "type": "integer"
      +}
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations only declare read-only and closed-world. The description adds substantial behavior: data-source coverage, that names stop after 1945, that later years are anonymized, that inferences are marked, and the summary/full-record split for multi-answer houses. No contradictions with annotations.

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 content is relevant and front-loaded, but the first sentence is extremely long and dense, packing many data sources and conditions into one run-on. It would be easier to scan if split into shorter sentences or bullets.

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 complex data-aggregation tool with no output schema, the description covers the return categories, coverage limits, anonymization rule, inference marking and pagination/multi-answer behavior. It is complete enough for an agent to call correctly, even without sibling guidance.

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 100%, so the schema already documents address formats, page and year. The description reinforces year's role in retrieving a single directory or census year and adds the multi-answer summary rule, which gives meaningful context for when to supply year.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and scope: a covered Vancouver house's build year, permit, fire-insurance map, current building, directory residents and census households. It is far more specific than the name alone, though it never mentions the sibling find_house or coverage, so an agent must infer when this is preferable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

It explains the multi-answer summary behavior and how to call again with year for other directory or census years, which is useful in-tool guidance. It does not explicitly say when to use this tool instead of find_house or coverage, nor does it state prerequisites for a covered address.

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