Skip to main content
Glama
Sign In

Desearch

by io.github.Desearch-ai
OverviewDiscussionsAdmin

Get Company Search Status

company-search-status
Read-only

Status, progress, and cost of one Company Search or Company Enrich task, plus a page of the companies delivered so far: domain, name, url, location, fit score (null for Company Enrich) and why it matched, primary_email and primary_contact, public emails, phones, and social profiles with the page each came from (source_url), leaders with their roles, title, LinkedIn profile, and emails (each with its verification status; inferred ones with source: inferred and a confidence), contact_coverage, and enrichment (status partial or complete, and each stage: profile, contacts, people, email_patterns, email_check). Free: it reads a task you already started and runs no new search. Cost fields are reserved_cost_usd and, once the task ended, final_cost_usd. The data came from each company's own website, public web search, and public LinkedIn profiles. Companies arrive while the task runs and are filled in place by the later stages: pass the returned next_cursor as cursor to get only the companies delivered since then, and call without cursor to read every company in its latest version. stage enriching means every company is delivered and only later stages of some are left. When done is true and has_more is false you have every company. An ended task has completion_reason (why it stopped; all_domains_processed for Company Enrich or a search restricted to the domains its query names, listed as only_domains), coverage_limited: true when a limit stopped it before count (more companies may match: the next hint says how to continue it with continue_from), and warnings. A search with a budget shows max_cost_usd, and progress.effort_units once it ended (the search effort billed where the companies delivered do not cover it); a continued search shows continue_from. Company Search results have fully_verified (every criterion confirmed by the company's own pages) and unverified_criteria (criteria that are unknown or not met, or a disqualifier that applies). These are information only: the company still qualified.

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": {
      "task_id": "<task_id>"
    },
    "name": "company-search-status"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoCompanies per page (1-100, default 10).
cursorNonext_cursor from the previous company-search-status call, to get only the companies delivered since then. Omit to read from the first company, each in its latest version.
task_idYestask_id returned by company-search or company-enrich, example: '5b33f3ee-168b-4780-9c8e-63a626781872'. A People Search task_id is not found here.
include_companiesNoSet false to read only the status, progress, and cost.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnly/non-destructive/openWorld, yet the description adds substantial behavior: the call is free and starts no new search, results are filled in place by later stages while the task runs, 'stage enriching' means all companies are delivered, and completion_reason / coverage_limited / warnings / max_cost_usd / effort_units / continue_from semantics are disclosed. It also explains that fully_verified and unverified_criteria are informational only and the company still qualified — a genuinely non-obvious behavioral caveat.

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?

The lead sentence is front-loaded and useful, but what follows is a single ~340-word paragraph that mixes return-field inventory, provenance, pagination, stage semantics, and cost rules with no visual separation. The cursor behavior is restated from the schema, and the provenance sentence ('each company's own website, public web search, and public LinkedIn profiles') is expensive relative to its decision value.

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 and a rich, multi-stage return object, the description carries the full burden and discharges it: it enumerates the company fields, the stage names, the cost fields, and the terminal/limited completion signals an agent needs to decide whether to keep polling. Little an agent needs to call or interpret this tool is missing.

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?

Coverage is 100%, so the schema already documents limit, cursor, task_id, and include_companies; the description nonetheless adds meaning beyond it, notably that omitting cursor returns companies 'each in its latest version' while a cursor returns only later deliveries, and that next_cursor is the value to feed back. It adds little for limit beyond what the schema states.

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?

Names a specific verb+resource combination ('status, progress, and cost of one Company Search or Company Enrich task') plus the payload (a page of delivered companies), and distinguishes itself from company-search by stating it 'reads a task you already started and runs no new search.' The task_id schema note that 'A People Search task_id is not found here' further separates it from people-search-status.

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 the operative poll patterns explicitly: pass the returned next_cursor as cursor to get only newly delivered companies, call without cursor to read every company in its latest version, and set include_companies=false to read only status/progress/cost. It also names the terminal condition ('When done is true and has_more is false you have every company'). It does not route the agent to company-search-tasks for discovery or to pause/resume/cancel siblings, but the core when/how is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Desearch toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources