Skip to main content
Glama
zoharbabin

Google Researcher MCP

Sequential Search

sequential_search

Track and document each step of a multi-stage research investigation, capturing findings, sources, and knowledge gaps to build on previous work across API calls.

Instructions

Track multi-step research progress across multiple API calls.

When to use:

  • Complex investigations requiring 3+ searches with different angles

  • Research you might abandon early (tracks partial progress)

  • Investigations where you need to show reasoning steps

  • Research with branching paths to explore alternatives

When to use search_and_scrape instead:

  • Simple queries that need content from multiple sources in one call

Key principle: You do the reasoning; this tool tracks state. It persists across API calls so you can build on previous steps.

Example flow:

  1. Start: sequential_search(searchStep: "Starting research on X", stepNumber: 1, nextStepNeeded: true)

  2. Search: search_and_scrape("topic")

  3. Record: sequential_search(searchStep: "Found Y, need Z", stepNumber: 2, source: {...}, nextStepNeeded: true)

  4. Complete: sequential_search(searchStep: "Research complete", stepNumber: 3, nextStepNeeded: false)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
searchStepYesDescription of what you searched or found in this step
stepNumberYesCurrent step number (starts at 1)
totalStepsEstimateNoEstimated total steps needed (can be adjusted as you go)
nextStepNeededYesSet to true if more research steps are needed, false when done
sourceNoSource found in this step (if any)
knowledgeGapNoKnowledge gap identified - what information is still missing
isRevisionNoSet to true if this step revises previous thinking
revisesStepNoStep number being revised (required if isRevision is true)
branchFromStepNoStep number to branch from (for exploring alternatives)
branchIdNoIdentifier for this branch of research
sessionIdNoSession ID to continue (optional - uses current session if omitted)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
sessionIdYesUnique session identifier
currentStepYesCurrent step number
totalStepsEstimateYesEstimated total steps
isCompleteYesWhether research is marked as complete
sourceCountYesNumber of sources collected so far
openGapsCountYesNumber of unresolved knowledge gaps
stateSummaryYesHuman-readable summary of research state
sourcesNoAll sources collected (included when complete)
gapsNoAll knowledge gaps (included when complete)
Behavior4/5

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

The description explains that the tool tracks state across API calls and provides an example flow. Annotations are minimal (readOnlyHint false), but the description adds context about persistence and step-by-step progress. It does not mention potential side effects like data retention limits, but overall it is sufficiently transparent.

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 well-structured with sections (When to use, When not to use, Key principle, Example flow). Every sentence provides value and it is front-loaded with the main purpose. No unnecessary words.

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?

Given the tool's complexity (11 parameters, nested objects, output schema), the description covers all necessary aspects: workflow, usage rules, parameter roles via example, and persistence. The output schema exists, so return values are documented elsewhere. The description is complete.

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

Parameters4/5

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

With 100% schema description coverage, the input schema already explains parameters. The description adds value through the example flow and key principle, showing how parameters like searchStep and stepNumber are used in sequence, which helps the agent understand the tool's usage pattern.

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 starts with 'Track multi-step research progress across multiple API calls' which clearly states the tool's verb and resource. It differentiates from sibling tools like search_and_scrape by specifying when to use each.

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?

The description explicitly lists when to use (complex investigations, 3+ searches, early abandonment, branching) and when to use an alternative (search_and_scrape for simple queries). This provides clear guidance on tool selection.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zoharbabin/google-researcher-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server