Crawdar Business Research

Research businesses from a brief

research_businesses

Read-only

Use for a quick synchronous search when the user supplies one natural-language brief and can wait for results in the current tool call. For durable progress, retry, export, or large agent workflows, use start_lead_search instead.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`brief`	Yes	Example: Independent veterinary clinics in Berlin with an active first-party website. Exclude directories and chains.
`limit`	No	Maximum businesses in this response page.
`fields`	No	Business fields to retain. Website and source evidence remain available for verification.
`offset`	No	Zero-based result offset for this response page.
`output`	No	Compact minimizes tokens. Full preserves every returned field.	compact
`geography`	No	Optional explicit geography. Use when the brief does not make location clear.
`includeDiagnostics`	No	Include source status and explained exclusions.

Output Schema

TableJSON Schema

Name	Required	Description
`limit`	Yes	Maximum prospects requested for this page.
`offset`	Yes	Zero-based offset of this page.
`hasMore`	Yes	Whether another result page is available.
`results`	Yes
`warnings`	Yes	Limitations the agent should retain with downstream data.
`requestId`	Yes	Request identifier for support and diagnostics.
`durationMs`	No
`nextOffset`	No	Offset for the next synchronous result page, or null when complete.
`diagnostics`	No	Source status and explained candidate exclusions.
`resultCount`	Yes	Total accepted prospects before response pagination.
`returnedCount`	Yes	Prospects returned in this response page.
`schemaVersion`	Yes	Version of the result contract.
`searchedSources`	Yes	Discovery and first-party source types consulted.
`remainingFreeSearches`	No

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, covering the safety profile. The description adds useful behavioral context beyond these flags: the tool is synchronous, returns in the current call, and is not built for durable progress or retry. This supplements the annotations without contradicting them.

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?

Two sentences with zero filler. The core usage condition is front-loaded, and the alternative routing is given immediately after. Every word contributes to tool selection.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the rich input schema and an output schema, the description adequately covers the key selection criteria: synchronous execution, one-shot nature, natural-language brief, and the durable alternative. The only gap is not explicitly differentiating from search_businesses, but the 'natural-language brief' qualifier partially covers that.

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% with detailed descriptions for all seven parameters including the brief format, pagination, output modes, and diagnostics. The description adds no parameter-level meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs a quick synchronous search from a natural-language brief, which is a specific verb+resource pairing. It explicitly names start_lead_search as the alternative for durable workflows, but does not distinguish from the similarly named sibling search_businesses, which could leave some ambiguity.

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 gives explicit when-to-use guidance ('quick synchronous search when the user supplies one natural-language brief and can wait for results in the current tool call') and explicit when-not-to-use guidance with a named alternative ('For durable progress, retry, export, or large agent workflows, use start_lead_search instead'). This leaves little to inference.

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?