PersonIQ

Deep dive intelligence (long-running)

deep_dive_intelligence

Exhaustive AI research pass over a person in an owned report. Every finding carries its source URL, so the output is checkable rather than asserted — report it with the citations attached and let the reader judge. Runs as a background job: returns a job id to poll with get_job. Costs 12 credits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "searchId": "<searchId>",
      "personId": "<personId>"
    },
    "name": "deep_dive_intelligence"
  }
}

Input Schema

Name	Required	Description
`format`	No	Rendering of the human-readable text channel. "prose" (default) is a compact summary an agent can reason over; "json" repeats the data verbatim; "report" is a formatted Markdown report to show a person; "html" is a standalone HTML document for saving, printing or PDF. Machine-readable structuredContent is always included either way.
`personId`	Yes	personId of the match to research.
`searchId`	Yes	searchId returned by search_person.
`confirmToken`	No	Omit to receive a quote. Pass the token from that quote to start the job.

Output Schema

Name	Required	Description	Default
`data`	Yes
`apiVersion`	Yes
`disclaimer`	Yes
`balanceNotice`	No
`suggestedNext`	No
`criminalCaveat`	No
`notConsumerReport`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations only declare the safety profile (readOnly false, openWorld true, destructive false); the description adds that execution is asynchronous, that a job id must be polled, and that it costs 12 credits — all facts an agent needs before calling and none of them in the structured fields. It does not say how long the job typically takes or what happens on failure, but the added context is substantive.

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?

Three compact sentences, front-loaded with what the tool does, then the citation guarantee, then the operational facts (background job, job id, credit cost). The aside 'let the reader judge' is editorial but does not obstruct comprehension.

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?

An output schema exists, so the description needn't describe return values, and it still supplies the key operational facts (async job, polling target, cost, citation provenance). Remaining gaps — job duration, failure behavior — are minor for a research tool whose schema is fully documented.

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% and the schema already explains format, confirmToken quoting, and the searchId/personId provenance. The description adds only the phrase 'owned report', which hints at the ownership prerequisite behind searchId but does not clarify the confirmToken quote-then-start flow that the schema spells out.

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?

States a specific verb and resource ('Exhaustive AI research pass over a person in an owned report'), which is far more informative than the title's 'Deep dive intelligence'. It does not, however, contrast itself with the closely named siblings get_person_intelligence and investigate_person, so the agent must infer the difference.

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

Usage Guidelines3/5

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

Implicitly scopes usage to a person inside an already-owned report and names the next step in the workflow ('returns a job id to poll with get_job'), which is genuinely useful guidance. It gives no explicit when-to-use versus get_person_intelligence or investigate_person, and no exclusions, so the routing decision is left to inference.

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

All PersonIQ 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?