Skip to main content
Glama

GoodLeads

Browse leads

browse_leads
Read-onlyIdempotent

Browse leads — rows for a shape or a saved list, or (summary=True) its counts, facets and price.

Two ways to say which records, one contract underneath:
  * a saved list — `list_id`, the 8-char id in `#browse?list=<id>`. Its states,
    filters, sort and inactive-or-holding toggle are read from the list;
    pass nothing else about the shape.
  * an inline shape — `filters` plus `state` (one state) or `states`
    (several); omit both for every live state (CO, CT, FL, NY, TX, VA).

`summary=True` returns the summary contract instead of rows — the same
numbers the buying surface shows, from the same code path: `matching`, `sellable`, `verified_one`, `verified_both`, `no_channel`, `unnamed`,
`facets`, `prices`, `quote` (present when `lane` or `cap` is given),
`exact`, `computed_at`, `quote_valid_until`, `per_state`. **Only `sellable`
— a matching record whose filing names a person — is ever billed or
delivered; never quote `matching` as a price.** name and address $0.25 per record · plus one verified phone or email $0.50 · plus both $0.70 (price rule v1; live prices always come from the summary call's `prices` block). Lanes: `all` / `best` / `contact`
(`all` = every sellable record at the name-and-address price; `best` =
each record at its own grade, verified first; `contact` = only records
with a verified phone or email). Cap: `{"type": "count|budget", "value"}`
— records for count, cents for budget. To buy, hand the same list / shape,
lane and cap to `create_checkout`.

Speak the canonical vocabulary — it is the same across every state:
`status` and `entity_type` take canonical values (`"active"`, `"LLC"`),
so `entity_type = "LLC"` matches Colorado's raw `DLLC`, Florida's `FLAL`,
and New York's spelled-out form alike; state-specific raw codes live
behind `status_raw` / `entity_type_raw` if you ever need them.
"Contacts for new businesses" / "decision-makers" = filter
`contact_relevance_tier in ["Decision Maker", "Likely Decision Maker"]` —
our scored is-this-the-right-person opinion, available in EVERY state.
(`role_is_decision_maker: true` is the stricter, title-attested variant:
it means the state's own filing lists an authority title. Several states —
Colorado and New York among them — publish no officer titles at all, so
filtering on it there returns zero and silently drops real decision-makers.
Layer it on top only when you specifically want title-attested records.)
When a filter touches a (field, value) the requested state never populates
by design (e.g. `entity_type="SOLE_PROP"` in TX), the payload additionally
carries `zero_reasons` — machine-readable notes saying WHY the count is
zero and the nearest alternative; the key is absent otherwise.
Add `has_phone` / `has_email` for reachable ones. Worked example — active
LLC decision-makers with a phone, across all states, excluding two sectors:

    browse_leads(filters=[
        {"field": "status", "op": "eq", "value": "active"},
        {"field": "entity_type", "op": "eq", "value": "LLC"},
        {"field": "contact_relevance_tier", "op": "in",
         "value": ["Decision Maker", "Likely Decision Maker"]},
        {"field": "has_phone", "op": "eq", "value": true},
        {"field": "industry_sector", "op": "not_in",
         "value": ["Real Estate", "Finance"]},
    ])

Filter grammar (rendered from the schema — `list_filterable_fields(section="grammar")` is the full contract): a leaf is `{"field", "op", "value"}`; the top-level filters list is an implicit `and` group; group nodes `{"op": "and", "filters": [...]}` and `{"op": "or", "filters": [...]}` nest one or more children, `{"op": "not", "filters": [<one leaf or group>]}` negates exactly one. Operators by field type — text: eq, neq, in, not_in, contains, does_not_contain, exists, missing; number: eq, neq, gt, gte, lt, lte, between, in, not_in, exists, missing; date: eq, neq, gt, gte, lt, lte, between, in, not_in, exists, missing; boolean: eq, neq; geo: within. Narrower pseudo-fields — `run_manifest_id` eq; `missing_stage` eq; `created_at` gt, gte, lt, lte, between; `geo_polygon` within; `geo_radius` within; `has_phone_or_email` eq. `neq`, `not_in`, `does_not_contain`, `not` keep rows where the field has no value. `exists` / `missing` take no value; `in` / `not_in` take a non-empty list; `between` takes `[start, end]`, both required. A (field, op) pair outside its type's row is a 422 naming the row, never a 500. Records appear here the morning after the state posts them — speed is measured from publication, never from filing.

Args:
    state: Two-letter state code (e.g. `FL`, `CO`) for one state.
    states: Several state codes (rows or summary). Omit both `state` and
        `states` for every live state.
    list_id: A saved list id. Mutually exclusive with `state` / `states` /
        `filters` — the list already carries them.
    filters: Filter clauses in the grammar above (leaves and `and` / `or` /
        `not` groups). Use `list_filterable_fields` to discover the
        77 fields, each one's enforced operators and allowed values.
    page: 1-based page number.
    page_size: Rows per page (1–200 with a key; capped at 25 on the free
        tier, default 50).
    sort: `[{"field", "dir"}]`, one or more keys over any of the 71 sortable fields (`asc` / `desc`); a bare field name still works with `sort_dir`. Tier fields sort by rank (reachability_tier On Fire > Very Hot > Hot > Warm > Cold; contact_relevance_tier Decision Maker > Likely Decision Maker > Probable Contact > Uncertain Contact > Unlikely Decision Maker; contact_confidence_tier Verified Contact > Likely Contact > Possible Contact > Uncertain Contact; industry_confidence_tier confirmed > likely > possible > unknown); lead_ref ASC is always appended (total order). An unknown field or direction is a 422 listing the sortable fields — never a silent fallback. Default `reachability_score` descending.
    sort_dir: `asc` or `desc` (default `desc`) — used when `sort` is a bare field name.
    include_non_operating: Include inactive or holding businesses
        (default False — only the records we sell). A saved list's own
        toggle wins when `list_id` is given.
    summary: Return the summary contract (counts, facets, prices, quote)
        instead of rows. Implied when `lane` or `cap` is given.
    lane: `all` / `best` / `contact` — asks the summary for a `quote`.
    cap: `{"type": "count|budget", "value": <int>}` — the dial the quote is
        solved against (records for count, cents for budget).

Returns:
    Rows: `{"items": [...], "total", "page", "page_size", "pages", "access_level",
    "_meta"}`. `_meta` is the provenance block every read carries:
    `schema_version` (the read-contract version — pin migrations to it),
    `freshness.data_refreshed_at` (when this state's data was last worked),
    `source` (public registry + derived-field attribution), `score_versions`,
    and `access_level` (preview = masked contacts, full = keyed). Keyless
    callers see `contact_name`, `email_primary`, `phone_primary` masked and may not filter the summary on them (422).
    Summary: the contract described above.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
capNo
laneNo
pageNo
sortNo
stateNo
statesNo
filtersNo
list_idNo
summaryNo
sort_dirNodesc
page_sizeNo
include_non_operatingNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is higher, but the description adds substantial behavioral context: only sellable records are billed or delivered, keyless callers see masked contacts, zero_reasons appear for impossible filters, and records appear the morning after state publication. It also discloses 422-versus-500 behavior, canonical vocabulary handling, and access-level differences, all beyond what annotations provide.

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?

Although long, the description is dense and efficiently structured with clear sections: core contract, canonical vocabulary, filter grammar, worked example, args, and returns. Every block earns its place by addressing a real decision an agent must make; there is no filler or restatement of schema fields.

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?

Given 12 parameters, 0% schema description coverage, and no actual schema descriptions, the description is exceptionally complete. It covers selection modes, summary contract fields, billing rules, filter operators by type, pseudo-fields, sorting semantics, response structure, access-level masking, freshness metadata, and error behavior. Nothing an agent needs to call this tool correctly appears missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for 12 parameters. The Args section explains each parameter's semantics, including mutual exclusivity of list_id with state/states/filters, page_size caps by tier, sort field ordering rules, lane meanings, cap shape, and summary implication. It even documents edge cases like unknown field/direction returning a 422 and the total-order tiebreak on lead_ref ASC.

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 description opens with a specific verb and resource: 'Browse leads — rows for a shape or a saved list, or (summary=True) its counts, facets and price.' It clearly distinguishes the row contract from the summary contract and signals that this is the lead-browsing entry point, not checkout or field discovery. It is far more than a restatement of the title and stands apart from siblings like find_lead_by_glid and create_checkout.

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?

The description explicitly provides two alternative ways to select records ('a saved list' vs 'an inline shape'), when to use summary, and when to pass lane/cap. It names related tools where relevant: 'Use list_filterable_fields to discover the 77 fields' and 'To buy, hand the same list / shape, lane and cap to create_checkout.' It also gives exclusions and defaults, such as omitting both state and states for every live state.

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