Skip to main content
Glama

Search projects in natural language

ai_search_projects
Destructive

Submits a natural-language search job and returns the job id. get_ai_search_result returns project records when the job finishes. limit is how many records to find (max 25) and is the spend. get_projects with q covers map-style filters (place, type, acres, dates). This tool applies when the question depends on wording inside the minutes. Each new or changed record counts toward 100,000 export records a month on County, State, and National plans. An unchanged record already delivered does not. Find Contact Info does not use credits on this call. On API Only and the trial, costs 1 credit per requested record. count_projects returns the structured count without records. notify.email=false skips the settlement email. Searches private leads by default. leadTypes (for example ["private","public"]) widens that set.

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": {
      "query": "<query>",
      "limit": "<limit>"
    },
    "name": "ai_search_projects"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoAlias of query.
cityNoCity integer ids from list_locations.
typeNoProject types from get_project_types.
limitYesRequired. Maximum records the job may deliver, 1-25. Credits are reserved for this many at submission and trued up to what actually delivers.
queryYesThe question in natural language — use this when they need evidence from the minutes, not for ordinary map-style filters.
stateNo
cityIdNo
countyNoCounty integer ids from list_locations.
dateToNo
notifyNo
offsetNo
statesNoState ids, names, or abbreviations — same as get_projects.
cityIdsNo
stateIdNo
subtypeNo
countyIdNo
dateFromNo
stateIdsNoAlias of states.
countyIdsNo
leadTypesNoLead types to include. Default ["private"] — private development only, same as the map. Widen it when they ask: ["private","public"] adds public-sector projects (schools, roads, utilities, civic facilities); ["private","private_minor"] adds small private jobs (single lots, tenant improvements, small additions); "public_minor" adds small public jobs. Infrastructure and Institutional/Public projects are mostly government-owned, so add "public" whenever you filter for them (propertyTypes Infrastructure or Institutional/Public, or constructionTypes infrastructure). Always keep "private" in the list — the API adds it back if you drop it. Standard and full records carry leadType and stage; compact omits them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / leadTypes / description
      Previous value: -"Lead types to include. Default [\"private\"] — private development only, same as the map. Widen it when they ask: [\"private\",\"public\"] adds public-sector projects (schools, roads, utilities, civic facilities); [\"private\",\"private_minor\"] adds small private jobs (single lots, tenant improvements, small additions); \"public_minor\" adds small public jobs. Always keep \"private\" in the list — the API adds it back if you drop it. Standard and full records carry leadType and stage; compact omits them."New value: +"Lead types to include. Default [\"private\"] — private development only, same as the map. Widen it when they ask: [\"private\",\"public\"] adds public-sector projects (schools, roads, utilities, civic facilities); [\"private\",\"private_minor\"] adds small private jobs (single lots, tenant improvements, small additions); \"public_minor\" adds small public jobs. Infrastructure and Institutional/Public projects are mostly government-owned, so add \"public\" whenever you filter for them (propertyTypes Infrastructure or Institutional/Public, or constructionTypes infrastructure). Always keep \"private\" in the list — the API adds it back if you drop it. Standard and full records carry leadType and stage; compact omits them."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=true, and the description substantiates why: it reserves credits at submission, counts records against a 100,000/month export cap, and charges 1 credit per requested record on API Only and trial. It also discloses the async job/settlement-email behavior and the notify.email=false opt-out. Minor gaps remain around job expiry, polling, and cancellation (cancel_ai_search is never mentioned).

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 the get_ai_search_result handoff are front-loaded correctly. However, the billing passage is dense and partly tangential ('Find Contact Info does not use credits on this call'), and the leadTypes discussion is long enough to bury the core usage rule for a reader skimming.

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 20-parameter async job tool with no output schema and no annotations beyond safety hints, the description covers the async pattern, result retrieval, credit reservation, monthly caps, notification opt-out, and the private-lead default. The notable omissions are offset pagination and job lifetime/cancellation.

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 coverage is only 45% across 20 parameters, so the description needs to carry more. It does add real meaning for leadTypes (default private, when to widen, the API re-adding 'private') and notify.email, and it clarifies query wording versus map-style filters, but offset, city/county/state ids, subtype, and dateFrom/dateTo are left undocumented in both places.

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 first sentence states a specific verb and resource ('Submits a natural-language search job and returns the job id') and immediately names the follow-up tool get_ai_search_result. It also distinguishes itself from get_projects and count_projects by carving out the 'wording inside the minutes' case, so an agent can route 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?

Explicit when-to-use ('applies when the question depends on wording inside the minutes'), explicit when-not ('get_projects with q covers map-style filters (place, type, acres, dates)'), plus a named alternative for counts (count_projects). Alternatives and exclusions are both present.

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