Skip to main content
Glama

HSH Data-on-Demand

by io.github.hshintelligence
OverviewDiscussionsAdmin

hsh-b2b-full

Every field a record carries, withheld from no tier: the person, the filed title, the company, the validated address where there is one, the firmographics, the detected tech stack, the stage, the hiring posture and the company's own profile link. A real sample on every call, priced on request. No personal telephone numbers (a company number only where its own site publishes one) and no revenue estimates — nothing here holds a person's number or a revenue figure, and a priced field nothing can fill is not a field we sell.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
liveNoRead each company's own site during the call (default true). Adds the company's current inbox, phone and links, each with provenance.
roleNoMatches the job title as stated on the filing (e.g. 'Chief Executive', 'Chief Financial').
sourceNo'both' (default), 'filings' for named officers with filed titles, or 'cohort' for founders with validated addresses.
tickerNoRestrict to one listed company.
dry_runNoReturn the sample and the quote without opening an order.
industryNoMatches the filed industry description, or the cohort's industry label.
locationNoCity, state or country. Cohort records only — filings do not carry a person's location.
quantityYesRecords wanted (1-100000). A real sample is returned now; the batch is quoted.
live_budgetNoHard ceiling on how many records get a live pass (default and maximum 25). Roughly five page fetches and two seconds each.
buyer_contactNoHow to reach you about the quote.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changed
    • addedInput schema / properties / buyer_contact
      Added value: +{
+  "description": "How to reach you about the quote.",
+  "type": "string"
+}
    • addedInput schema / properties / dry_run
      Added value: +{
+  "description": "Return the sample and the quote without opening an order.",
+  "type": "string"
+}
    • removedInput schema / properties / funding_stage
      Removed value: -{
-  "description": "",
-  "type": "string"
-}
    • changedInput schema / properties / industry / description
      Previous value: -""New value: +"Matches the filed industry description, or the cohort's industry label."
    • addedInput schema / properties / live
      Added value: +{
+  "description": "Read each company's own site during the call (default true). Adds the company's current inbox, phone and links, each with provenance.",
+  "type": "string"
+}
    • addedInput schema / properties / live_budget
      Added value: +{
+  "description": "Hard ceiling on how many records get a live pass (default and maximum 25). Roughly five page fetches and two seconds each.",
+  "type": "number"
+}
    • addedInput schema / properties / location
      Added value: +{
+  "description": "City, state or country. Cohort records only — filings do not carry a person's location.",
+  "type": "string"
+}
    • changedInput schema / properties / quantity / description
      Previous value: -""New value: +"Records wanted (1-100000). A real sample is returned now; the batch is quoted."
    • removedInput schema / properties / revenue_range
      Removed value: -{
-  "description": "",
-  "type": "string"
-}
    • addedInput schema / properties / role
      Added value: +{
+  "description": "Matches the job title as stated on the filing (e.g. 'Chief Executive', 'Chief Financial').",
+  "type": "string"
+}
    • addedInput schema / properties / source
      Added value: +{
+  "description": "'both' (default), 'filings' for named officers with filed titles, or 'cohort' for founders with validated addresses.",
+  "type": "string"
+}
    • removedInput schema / properties / tech_stack
      Removed value: -{
-  "description": "Filter by tech they use (e.g., 'Shopify', 'Salesforce').",
-  "type": "string"
-}
    • addedInput schema / properties / ticker
      Added value: +{
+  "description": "Restrict to one listed company.",
+  "type": "string"
+}
  2. Added

TDQS

C2.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose key constraints: it excludes personal phone numbers and revenue estimates, and states that a real sample is returned on every call with pricing on request. It also hints at order behavior through the dry_run parameter ('without opening an order'). However, it does not explicitly warn that a normal call will open an order or describe any side effects beyond that, so it is only moderately transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense, run-on paragraph with no headers or bullet points. It front-loads 'Every field a record carries' but then rambles through a long list and exclusions without breaking them down. The critical information about exclusions is buried in the middle, and the pricing/order concept appears only at the end. This is verbose and poorly structured for an AI agent that needs to parse it quickly.

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?

The description covers the essential operational context: that a real sample is returned immediately, that the batch is quoted, and that dry_run returns sample+quote without opening an order. It also clarifies the scope of data (filings vs. cohort). However, with 10 params and no output schema, it does not describe the response format beyond 'real sample' and 'quote' – it never explains what the sample structure looks like or how the record fields map to the schema. For a tool with this complexity, it is adequate but not complete.

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?

The schema has 100% coverage with descriptions for all 10 parameters, so the baseline is 3. The tool description adds context about the overall data fields but does not clarify individual parameter semantics beyond what the schema already provides. For example, 'live' and 'live_budget' are not expanded in the description, even though they may interact in ways not obvious from the schema alone. It does not degrade, but it does not improve either.

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

Purpose3/5

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

The description enumerates the data fields and exclusions but never states the action the tool performs (e.g., 'fetches', 'provides', 'quotes'). It reads more like a data sheet than a tool definition, leaving the agent to infer the operation from the name and schema. It does distinguish itself as 'full' coverage, but without a clear verb+resource it is only vaguely purposeful.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance, and no mention of sibling tools like hsh-b2b-enriched or hsh-b2b-contact. The phrase 'withheld from no tier' hints at a comparison, but it never tells the agent when to prefer this over alternatives. The description implies it is the comprehensive option but leaves the decision entirely to inference.

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

All HSH Data-on-Demand 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