Skip to main content
Glama

Data Search

spur_data_search

Search properties across Spur's data providers in one search. Set listing_status to search current listings (ZHomes); leave it out to search off-market and owner records, routed automatically to the best source (county records, distress data) or to the provider the user named.

Each value is labeled with the provider that supplied it. Filters return three states: matched, unknown (could not be checked, shown separately), or excluded. Costs 1 search credit plus data credits per record returned; an empty page is free. Requires confirm=true after the user approved running the search. Follow with spur_save_data_results to keep results as properties.

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": {
      "location": "<location>",
      "confirm": "<confirm>"
    },
    "name": "spur_data_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
cursorNoNext-page cursor returned by the preceding search; keep the same filters
confirmYesSet to true ONLY after the user explicitly approved running this search. Never assume approval.
filtersNoData Search filters, e.g. from spur_parse_data_search: minPrice, maxPrice, minBeds, minYearsOwned, minEquityPercent, offMarketOnly, transferredWithinDays, preForeclosureWithinDays, conditions[]
locationYes
providerNoProvider key from spur_list_data_providers, only when the user asked for one
table_idNoAppend this page to an existing search table
page_sizeNo
keep_tableNoKeep the search as a table and record returned signed rows
selectionsNo
listing_statusNoOnly for listing searches; omit for off-market and owner records

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

Adds real cost and result semantics beyond the annotations: 1 search credit plus data credits per record, an empty page is free, each value is labeled with its source provider, and filters return matched/unknown/excluded states rather than silently dropping rows. However, the description of the mandatory confirm gate repeats the schema's own confirm description, and it does not reconcile the credit-consuming, table-persisting behavior with the declared destructiveHint=false or explain the table lifecycle. Useful, but partly overlapping structured data.

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

Conciseness5/5

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

Two paragraphs, front-loaded with the core action and the mode-selection rule, then cost/approval/follow-up. No filler sentences; each clause carries a distinct operational fact (routing, labeling, filter states, credits, confirm, next step).

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?

Covers the hard parts of a 10-parameter, nested-object, credit-charging, non-idempotent search: approval gating, cost model with a free-empty-page exception, provider attribution, three-state filter results, and the persistence follow-up. Remaining gaps are seeding the search from spur_parse_data_search and when to use cursor/table_id for pagination, neither of which is signaled despite being nested, non-obvious parameters.

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?

Explains the semantic consequence of listing_status (present = ZHomes listings, absent = off-market/owner records with automatic routing), which the schema only states as "omit for off-market and owner records" without the routing implication. The provider parameter's constraint (only when the user asked for one) is restated from the schema rather than extended. With 70% coverage, the description lifts the key routing parameter above the schema baseline but leaves cursor, table_id, keep_table, and selections untouched.

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?

Names a specific verb and resource: "Search properties across Spur's data providers in one search," and the listing_status sentence narrows the two operating modes (on-market listings vs off-market/owner records). It never names a sibling such as spur_search_properties or spur_search_phone_numbers, so an agent must infer the boundary from behavior alone.

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 a concrete selection rule: include listing_status for current listings (ZHomes), omit it for off-market and owner records, and pass provider only when the user named one. It also states the sequencing requirement (confirm=true only after explicit user approval) and the follow-up path to spur_save_data_results. No explicit statement of when to prefer this over other search tools exists, but the conditions it does give are decisive.

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