Desearch

List Company Search Tasks

company-search-tasks

Read-only

Your Company Search and Company Enrich tasks, newest first, with status, counts, cost, why each ended task stopped (completion_reason, coverage_limited), max_cost_usd and continue_from when a search set them, and the metadata labels set on company-search or company-enrich. Free; it lists your own tasks, not the companies they found (read those with company-search-status). People Search tasks are not listed here (see people-search-tasks). Use it to find a task_id (filter by type, status, or metadata to find the tasks of one campaign), or to see which tasks are still queued, running, or paused: a new task is refused while too many People Search and Company Search tasks are active.

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": "company-search-tasks"
  }
}

Input Schema

Name	Required	Description
`type`	No	Only Company Search ('search') or only Company Enrich ('enrich') tasks.
`limit`	No	Tasks per page (1-100, API default 20).
`cursor`	No	next_cursor from the previous page. Keep the same type, status, and metadata filters when you page.
`status`	No	Only tasks in these statuses, example: ['running', 'paused'].
`metadata`	No	Only tasks whose metadata has all of these key/value pairs (exact match, up to 3), example: {"campaign": "q4-outbound"}.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 29, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint false), but the description adds real behavior: the call is free, results are ordered newest first, and each row includes completion_reason, coverage_limited, max_cost_usd, continue_from, and metadata labels. The concurrency note about new tasks being refused while too many are active is useful operational context. It stops short of stating pagination limits or default page size, which the schema covers instead.

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 what is returned, then the exclusions, then the use cases. The middle clause enumerating returned fields is long and slightly run-on, but every element (cost, completion_reason, continue_from, metadata) tells the agent something it would otherwise have to guess, given there is no output schema.

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 carries the burden of describing return contents and does so field by field, plus ordering, cost, and the pagination-adjacent continue_from semantics. For a read-only list tool with five optional filters, nothing material 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?

Schema coverage is 100%, so the baseline is 3, but the description adds intent beyond the field definitions by explaining that type/status/metadata filtering is how you isolate the tasks of a single campaign. It does not restate enum values or cursor mechanics, which is appropriate since the schema handles those.

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 (list your Company Search and Company Enrich tasks) plus ordering (newest first) and the fields each row carries. It explicitly distinguishes itself from two siblings by saying it does not return the companies found (use company-search-status) and does not list People Search tasks (use people-search-tasks).

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 two concrete use cases: find a task_id (filtering by type, status, or metadata for one campaign) and monitor which tasks are queued, running, or paused. It also discloses the downstream consequence that a new task is refused while too many tasks are active, and names the alternatives for the two things it does not do.

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

All Desearch tools Inspect

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.