Skip to main content
Glama

Run a Data Search job

spur_run_data_job
Destructive

Start a recipe job immediately. Every enabled step runs automatically, including owner contact enrichment and Do Not Call checks by default; set includeContacts=false to skip contacts. Recipes (key: params besides location, maxCandidates, unknownPolicy, includeContacts):

  • motivated_seller: off-market, owned a long time, high estimated equity (minTenureYears, minEquityPercent)

  • absentee_owner: owner lives elsewhere, usually landlords (minTenureYears)

  • pre_foreclosure: recent default or foreclosure filing with equity left (withinDays, minEquityPercent)

  • free_and_clear: owned outright or nearly paid off (maxLtvPercent)

  • vacant_property: reported vacant

  • entity_owned: owned by an LLC, corporation or trust; includeContacts finds the people behind it (entityTypes, minTenureYears)

  • neighbor_farming: every home within radiusMiles (default 0.25) of one property, with owner names, owner mailing address and estimated loan balance; location must include street plus state or ZIP; includeContacts adds phones and emails (radiusMiles) Uses data credits as lookups complete. No separate approval or confirm flag is required to run the recipe. A job_id starts a legacy job that is still awaiting approval. Poll with spur_get_data_job. Matched items are always saved to the user's properties when the job finishes (free), and also added to save_to_list_id when given; unknown items are saved to unknown_list_id only when given.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "spur_run_data_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idNoExisting legacy job to start
paramsNoRecipe parameters, e.g. minTenureYears, minEquityPercent, withinDays, maxLtvPercent, entityTypes, radiusMiles, maxCandidates, includeContacts
confirmNoLegacy compatibility flag; recipes run without this flag.
locationNo
recipe_keyNomotivated_seller
selectionsNo
idempotency_keyNoReuse for retries of the same job to avoid duplicate execution
save_to_list_idNo
unknown_list_idNo
budget_limit_microsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false, and readOnlyHint=false, so the write/irreversible profile is structured data. The description adds genuinely non-obvious behavior: credits are consumed as lookups complete, no separate confirm flag is needed, matched items are always persisted to properties, and unknown items go to unknown_list_id only when supplied. It stays at 3 because it omits cost/scope controls (budget_limit_micros, selections) that materially affect how the destructive run executes.

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?

Front-loads the action, then uses a compact bulleted recipe table followed by credits/persistence/polling notes, so the length is mostly earned by real per-recipe distinctions. It is dense but skimmable; a few clauses (legacy job_id, confirm flag) could be tightened.

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 10-parameter mutation with nested selection objects and no output schema, the description covers default behavior, side effects (auto-save to properties), cost model, and polling guidance. It does not explain the selections provider object or budget_limit_micros, which an agent would need for cost-controlled runs.

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?

With only 40% schema coverage across 10 parameters, the description compensates well: it maps recipe-specific params (minTenureYears, minEquityPercent, withinDays, maxLtvPercent, entityTypes, radiusMiles) to their recipes, explains includeContacts, save_to_list_id, unknown_list_id, and the legacy job_id/confirm behavior. It leaves selections, idempotency_key, and budget_limit_micros unexplained, so it is strong but not complete.

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?

States a specific verb and resource ("Start a recipe job immediately") and enumerates the seven recipe keys with what each targets, so an agent knows exactly which capability and variant it is invoking. It also names the sibling used for polling (spur_get_data_job), separating the start action from the follow-up action.

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?

Gives per-recipe selection guidance (motivated_seller = long tenure/high equity, absentee_owner = landlords, neighbor_farming = radius around a single property, etc.) plus the constraint that neighbor_farming requires a street plus state or ZIP. It also states the default behavior (includeContacts=true, DNC checks on) and how to opt out, leaving little to inference.

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