StackFast FractWin Expert Brain

Talent Scout Discover Local Companies

talent_scout_discover_local_companies

Read-onlyIdempotent

Preview the account owner's saved local business-list campaign. Returns public company websites only, with size-band confidence and source receipts for manual review. Read-only by default; set persist_results true only for an intentional store update.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No
`sources`	No
`tenant_id`	No
`campaign_id`	No
`sqlite_path`	No	Optional local SQLite path for BYOC receipts; hosted cloud calls fail closed instead of reading local files.
`campaign_name`	No
`auth_token_key`	No	Optional wallet/env key name for the tenant Turso auth token. Never pass a raw token.
`radius_minutes`	No
`persist_results`	No	When true, persist discovered company records to the Talent Scout campaign store. Defaults false so hosted MCP discovery remains a read-only preview for human review.
`company_size_max`	No
`company_size_min`	No
`database_url_key`	No	Optional wallet/env key name for the tenant Turso database URL. Never pass a raw URL or secret.
`geography_anchor`	No
`target_role_lanes`	No
`allow_live_firecrawl`	No	Backward-compatible refresh flag; Firecrawl is only a fallback/search or downstream extraction provider, not the Stage 1 radar.
`target_company_lanes`	No
`tenant_database_type`	No	Optional physical database routing mode. Omit for the default internal StackFast DB; use sovereign_cloud only with wallet-resolved tenant DB credentials.
`allow_live_google_places`	No	Refresh public business website leads through the configured directory provider and distance check. Websites are required before downstream enrichment.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	No
`public_tool`	Yes
`drafts_never_sends`	No
`no_autonomous_outbound`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 8, 2026

changedInput schema / properties / persist_results / description

Previous value: -"When true, persist discovered company leads to the Talent Scout campaign store. Defaults false so hosted MCP discovery remains a read-only preview for human review."New value: +"When true, persist discovered company records to the Talent Scout campaign store. Defaults false so hosted MCP discovery remains a read-only preview for human review."

Changed2 schema fields changedJul 1, 2026

changedInput schema / properties / allow_live_firecrawl / description

Previous value: -"Backward-compatible live flag; Firecrawl is only a fallback/search or downstream extraction provider, not the Stage 1 radar."New value: +"Backward-compatible refresh flag; Firecrawl is only a fallback/search or downstream extraction provider, not the Stage 1 radar."

changedInput schema / properties / allow_live_google_places / description

Previous value: -"Run the Blue Ocean Stage 1 radar through Google Places + Distance Matrix. Websites are required before downstream enrichment."New value: +"Refresh public business website leads through the configured directory provider and distance check. Websites are required before downstream enrichment."

Changed1 schema field changedJul 1, 2026

addedInput schema / properties / persist_results

Added value: +{
+  "default": false,
+  "description": "When true, persist discovered company leads to the Talent Scout campaign store. Defaults false so hosted MCP discovery remains a read-only preview for human review.",
+  "type": "boolean"
+}

Changed2 schema fields changedJun 25, 2026

addedInput schema / properties / allow_live_firecrawl / description

Added value: +"Backward-compatible live flag; Firecrawl is only a fallback/search or downstream extraction provider, not the Stage 1 radar."

addedInput schema / properties / allow_live_google_places

Added value: +{
+  "default": false,
+  "description": "Run the Blue Ocean Stage 1 radar through Google Places + Distance Matrix. Websites are required before downstream enrichment.",
+  "type": "boolean"
+}

AddedJun 25, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already provide readOnly/openWorld/idempotent/non-destructive. The description adds real value beyond them: the conditional write path (persist_results default false, only for intentional store update), the restricted return scope (public websites only, with receipts for review), and the preview workflow intent. 'Read-only by default' refines rather than contradicts readOnlyHint=true, so no contradiction flag.

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?

Three sentences, each earning its place: verb+resource in sentence one, result contents in sentence two, and the persistence caveat in sentence three. Front-loaded, no filler, no restating of the tool name.

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

Completeness3/5

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

Rich annotations plus an output schema already cover safety and return values, and the description handles workflow, result scope, and the persistence opt-out. The genuine gap is failing to differentiate from talent_scout_discover_companies_by_campaign, which appears immediately in the sibling list and could be selected wrongly; the live-refresh trade-offs are also left entirely to the schema. Adequate but not complete for an 18-parameter tool.

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 only 39%, so the description carries partial burden for the other 11 parameters. The phrase 'saved local business-list campaign' hints at campaign_id/campaign_name and geography/radius intent, but the description maps to no specific parameter and gives no guidance on the many filter and tenant-routing params, so it only partially compensates for the coverage gap.

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?

Specific verb 'Preview' plus a specific resource: the account owner's saved local business-list campaign. It also states the result scope (public company websites only, size-band confidence, source receipts for manual review), which helps an agent distinguish it from the near-sibling talent_scout_discover_companies_by_campaign through the 'saved local' framing.

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?

Clear usage context: use this to preview a saved local campaign for manual human review, and keep it read-only unless the agent intentionally wants a store update via persist_results. However, it never names an alternative or says when NOT to use it, so the very similar sibling talent_scout_discover_companies_by_campaign is left undisambiguated.

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

All StackFast FractWin Expert Brain 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.

Resources

Need Help?