Skip to main content
Glama

SourceGeek

Search candidates (precision)

precision_search_leads
Read-only

Higher-precision CoreSignal candidate search using the reasoning endpoint. Interprets the natural language query more carefully than the fast search and returns better-matched candidates plus an explanation of how it interpreted the query. More expensive and rate-limited (~10/hour) — use when match quality matters. Returns the matched candidates as CSV (Name, Title, Company, Location and profile URL) plus a searchId; it does not create a sheet. totalMatches is how many profiles the interpreted query matched before paging: 0 means the criteria as phrased matched nobody, so relax the query rather than repeat it. Spends the workspace's credits and stores the results in SourceGeek so a sheet saved later can carry the full candidate details.

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>"
    },
    "name": "precision_search_leads"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoRequested number of candidates to return (1-20). Defaults to 10 when omitted. The data source returns at most 20 results per search.
queryYesNatural language search query, e.g. 'VP Engineering at B2B SaaS companies in Amsterdam with 50-500 employees'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Beyond readOnlyHint/openWorldHint, it discloses that the call spends workspace credits, persists results in SourceGeek, and does NOT create a sheet — the kind of side-effect detail an agent needs before invoking. It omits what happens on rate-limit failure or how long stored results persist, keeping it short of a 5.

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-loaded with purpose and the fast-vs-precision tradeoff, then return semantics, then cost side effects — a sensible order. It is dense and slightly run-on in the final sentences, but nearly every clause carries actionable information.

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?

With no output schema, the description takes on return-value explanation and does so fully: CSV fields, searchId, and the meaning of totalMatches including the zero-case. Cost, rate limit, and persistence are also covered, leaving nothing critical for correct invocation unstated.

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 100% and the query parameter's example and length bounds are already in the schema; the description adds only the general notion that the query is interpreted in natural language. The paging hint via totalMatches is return-value semantics rather than parameter meaning, so baseline 3 applies.

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 ("CoreSignal candidate search using the reasoning endpoint") and immediately contrasts it with "the fast search," so the agent can distinguish it from fast_search_leads without opening either schema. The scope of returned data (CSV columns, searchId) is also named.

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 an explicit selection rule — "use when match quality matters" — paired with the cost tradeoff ("more expensive and rate-limited (~10/hour)") and the named alternative (fast search). It also tells the agent what to do with a zero result: "0 means the criteria as phrased matched nobody, so relax the query rather than repeat it."

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