Crawdar Business Research

Start a durable lead search

start_lead_search

Use for the recommended durable asynchronous workflow. Creates a private queued search job and returns a job id plus jobToken for progress polling, cursor paging, refinement, retry, cancellation, and CSV or JSON export.

Input Schema

TableJSON Schema

Name	Required	Description
`brief`	No	Natural-language business, geography, required signals, and exclusions. Use this instead of separate target and geography.
`limit`	No	Maximum accepted prospects retained by the job.
`fields`	No	Business fields to retain. Website and source evidence remain available for verification.
`target`	No	Business type or concise ideal-customer target. Pair with geography when brief is omitted.
`geography`	No	City, region, country, or Worldwide. Required with target when brief is omitted.
`qualifier`	No	Publicly verifiable requirements and exclusions.
`idempotencyKey`	No	Stable key for safely retrying the same job creation request.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Stable job identifier. Use it with jobToken in every lifecycle call.
`status`	Yes	Current durable job state.
`cacheHit`	No
`jobToken`	No	Private bearer token required to read, refine, or export this job.
`retryUrl`	Yes	Authenticated REST URL for creating a replacement after retryable failure.
`cancelUrl`	Yes	Authenticated REST URL for canceling queued or running work.
`exportUrl`	Yes	Authenticated CSV export URL. Add format=json for JSON.
`statusUrl`	Yes	Authenticated REST URL for job status and result pages.
`resultCount`	No
`expiresInSeconds`	Yes	Seconds until the private job and token expire.

TDQS

A4.5/5.0

Behavior5/5

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

The description goes well beyond the sparse annotations by disclosing that the tool creates a job, that the job is private and queued, and that it returns both a job id and jobToken enabling polling, paging, refinement, retry, cancellation, and export. This gives the agent a realistic model of the tool's side effects and follow-up capabilities. No contradiction with annotations exists.

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?

The entire description is one focused sentence that front-loads the usage recommendation before stating the core behavior and return value. Every phrase earns its place, and there is no redundant restating of parameter names or schema details.

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 that an output schema exists and all parameters are fully documented in the input schema, the description is complete for an agent to understand when and how to invoke the tool. It supplies the essential workflow context—durable asynchronous job creation, uniqueness of the job id/jobToken, and the available follow-up operations—without needing additional detail.

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 description coverage is 100%, and every parameter already has a meaningful description in the input schema. The tool description intentionally avoids repeating parameter details, which is appropriate, but it also adds no extra semantic value beyond what the schema already provides.

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 uses a specific verb-resource pair, 'creates a private queued search job', and clearly frames this as the durable asynchronous workflow. It distinguishes itself from sibling tools like search_businesses and research_businesses by emphasizing that it returns a job id and jobToken for later polling, paging, refinement, retry, cancellation, and export.

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?

The opening phrase 'Use for the recommended durable asynchronous workflow' gives clear usage context and implies this tool is preferred when an asynchronous job is desired. It does not explicitly name alternatives or state when not to use it, but the guidance is sufficient to route an agent appropriately among the siblings.

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

All Crawdar Business Research tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation4/5

Most tools map to distinct lifecycle actions (start/get/cancel/refine/retry), and the descriptions make those boundaries clear. The only real overlap is between research_businesses and search_businesses, which both perform synchronous lookups but are separated by natural-language vs structured input.

Naming Consistency5/5

All tools follow a consistent verb_noun snake_case pattern, with lead_search reused across lifecycle operations. Even explain_crawdar and sandbox_businesses fit the naming convention well.

Tool Count5/5

Nine tools is well within the appropriate range for a business-research MCP server. The count balances synchronous search, a durable async job lifecycle, sandbox testing, and self-documentation without feeling bloated.

Completeness4/5

The async lead-search lifecycle is well covered with start, get, cancel, refine, and retry, and the synchronous and sandbox search tools cover adjacent needs. However, export is mentioned in start_lead_search but not exposed as a tool, and there is no way to list existing jobs, leaving minor gaps.

Resources

Need Help?