Anakin

Official

Overview Schema Source Related Servers Discussions Admin

agentic_search

Read-only

Run multi-source deep research: search the web, scrape citations, and compile structured answers. Ideal for comparative analysis, multi-jurisdictional research, or market intelligence when a single URL or flat result is insufficient.

Instructions

Run multi-source deep research. The pipeline searches the web, scrapes the most relevant citations, and uses an LLM to structure the combined data into a unified answer. Async — typically 1–5 minutes. Use this when one URL or a flat search result will not answer the question (comparative analysis, multi-jurisdictional research, market intelligence). Returns a summary plus structured_data conforming to the inferred or supplied schema.

Input Schema

TableJSON Schema

Name	Required	Description
`prompt`	Yes	The research question or task in natural language.
`schema`	No	Optional JSON Schema describing the desired output shape. If omitted, the engine infers a schema from the prompt.
`useBrowser`	No	Use the headless browser when scraping cited pages (more reliable for JS-heavy sources). Defaults to true.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	Yes
`cached`	No
`status`	Yes
`summary`	No	AI-written summary of the research findings.
`data_schema`	No	Echo of the schema used to extract structured_data.
`structured_data`	No	Structured data matching the request's optional/inferred schema.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.1Sep 22, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations establish readOnlyHint and openWorldHint; the description goes beyond them by disclosing the asynchronous nature (1–5 minutes), the three-stage pipeline, and the return shape (summary plus structured_data conforming to the schema). Nothing contradicts the annotations.

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?

Five short sentences front-load the core purpose, then cover latency, usage conditions, and output shape. Every sentence carries distinct information; examples are parenthetical and do not bloat.

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?

For a complex multi-stage tool, the description covers purpose, when to choose it, async behavior, and output format. The input schema and output schema supply parameter/return detail, so nothing essential is missing for invocation.

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 100%, so the schema already explains prompt, schema, and useBrowser. The description adds only the link between a supplied schema and the structured_data output; that is useful but does not materially deepen parameter semantics.

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 opening verb "Run multi-source deep research" plus the pipeline description (search the web, scrape citations, LLM-structure results) identifies a distinct capability from search/scrape/crawl. The "when one URL or a flat search result will not answer the question" clause further separates it from single-source tools.

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

Usage Guidelines5/5

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

It explicitly states the triggering condition and gives concrete use cases (comparative analysis, multi-jurisdictional research, market intelligence). It also implies the negative case: if one URL or a flat search result suffices, this tool is overkill. It calls out async latency so the agent can weigh it.

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