Skip to main content
Glama

deep_osint

Run a browser-driven OSINT investigation by searching sources, crawling top results, extracting and cross-checking entities, analyzing page images, and returning leads for verification.

Instructions

Full browser-driven OSINT run: search, crawl sources, cross-check, image analysis.

  1. Searches in Chromium (DDG/Bing/Brave), 2) opens the top results and follows relevant links, 3) extracts text/entities/key sentences, 4) cross-checks entities across sources, 5) analyzes page images (EXIF/OCR/QR/hashes), 6) returns leads. Caps keep it bounded; use narrower tools for a single page or image.

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": {
      "query": "<query>"
    },
    "name": "deep_osint"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes
max_depthNo
max_pagesNo
ocr_imagesNo
max_resultsNo
screenshotsNo
analyze_imagesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden. It does well on the process shape and on signaling that it returns 'leads' rather than raw pages, but it says nothing about cost, latency, network/browser requirements, whether screenshots are written to disk, or what happens when a site blocks Chromium. For a multi-stage browser automation tool this is meaningful missing context, though the pipeline outline is genuinely informative.

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?

Front-loaded with the one-line summary, then a compact numbered pipeline that maps to real stages, followed by a single routing sentence. Every element earns its place; only minor redundancy in restating 'image analysis' in the header and again in step 5.

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?

For a seven-parameter, no-output-schema orchestration tool this covers the process but leaves two significant holes: no meaning for any tuning parameter and no sense of runtime cost or failure modes. An agent can decide whether to call it, but not how to configure it correctly on the first attempt.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and all seven parameters are bare titles with defaults. The description's only gesture toward them is 'Caps keep it bounded,' which does not explain what max_depth vs max_pages vs max_results control, nor what disabling ocr_images, screenshots, or analyze_images costs the agent. With near-zero schema help, the description needed to compensate and does not.

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 states a specific verb and resource — a browser-driven OSINT run — and enumerates the six concrete stages (search, crawl, extract, cross-check, image analysis, return leads). An agent can immediately tell this is an orchestration pipeline rather than a single-page primitive like browser_search or browser_extract.

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?

It gives an explicit routing rule: 'use narrower tools for a single page or image,' which tells the agent when this tool is the wrong choice. It also notes 'Caps keep it bounded,' implying the tool is scoped. It stops short of saying when this tool is preferable to a full alternative pipeline such as recon_deep, leaving the boundary between the two heavy-weight tools to inference.

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