Skip to main content
Glama
SanggonBoy

PyreCrawl

by SanggonBoy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

deep_research

Search the web and pull top sources as evidence for research, fact-checking, or deep-dives. Use multi-pass iterations to refine queries and gather deduplicated citations.

Instructions

Search the web, then pull the top sources as EVIDENCE (no LLM synthesis).

PRIMARY RESEARCH TOOL — use when the user asks to research, investigate, deep-dive, fact-check, or learn about a topic. Returns a citations list with stable [n] numbers and an evidence list of per-source markdown — the agent does the synthesis from evidence.

Multi-pass mode: set iterations=2-3 to auto-run additional searches with refined queries (alternatives, criticism, latest developments) and append deduplicated evidence. Each pass adds up to scrape_top new sources.

Args: query: search string. limit: how many search results to fetch. scrape_top: how many of those to actually fetch content from. prefer: "auto" | "fast" | "stealth" | "llm". iterations: 1 (default, single pass), 2-3 (multi-pass with refined queries targeting evidence gaps). Each pass searches from a different angle and deduplicates by URL.

Returns: {query, iterations_run, queries: [str], hits: [{url, title, snippet}], citations: [{url, title}], evidence: [{url, title, markdown}], scraped, used_engines, elapsed_ms} or {error, query, hint} on failure.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYes
preferNoauto
iterationsNo
scrape_topNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.0
    • addedInput schema / properties / iterations
      Added value: +{
+  "default": 1,
+  "title": "Iterations",
+  "type": "integer"
+}
  2. First observedv0.7.1

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and it delivers: it discloses that no LLM synthesis occurs, that multi-pass runs refine queries and deduplicate by URL, and that failures return a structured error object with a hint. This gives an agent a realistic model of what the tool will and will not do.

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?

The description is organized with a purpose statement, usage trigger, mode explanation, per-argument semantics, and a complete return shape. While long, every section earns its place and the most important decision-relevant facts are front-loaded.

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

Completeness5/5

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

The tool has five parameters, multiple modes, and a rich return value, and the description covers all of them: arguments, multi-pass behavior, output shape, and error shape. Nothing an agent needs to invoke or interpret the result is missing, and the output schema is effectively described inline.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must document all five parameters and does: query, limit, scrape_top, prefer (with listed option values), and iterations (with concrete guidance on 1 vs 2-3). The iterations explanation adds behavior beyond the schema's bare integer type.

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 opens with a specific verb and resource: 'Search the web, then pull the top sources as EVIDENCE (no LLM synthesis).' It clearly distinguishes this tool from generic search or scrape siblings by labeling it the 'PRIMARY RESEARCH TOOL' and explicitly stating the agent performs synthesis from evidence.

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 explicit trigger conditions: 'use when the user asks to research, investigate, deep-dive, fact-check, or learn about a topic.' It also explains the multi-pass option for deeper research. However, it does not explicitly name sibling alternatives or state when not to use this tool, so it stops short of full exclusion guidance.

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

Deploy Server

Other Tools