a9n9 Deep Research

Start Paid Deep Research

a9n9_research_start

Idempotent

Start bounded paid research in a real remotely hosted Browserbase Chromium session with JavaScript rendering, DOM interaction, scrolling, and dynamic-content extraction, followed by gpt-5.6-luna synthesis. targetUrl is optional; without it the quoted plan of public start URLs derived from the objective is executed. Call a9n9_research_quote first when price visibility is needed. The service does not bypass CAPTCHAs, logins, paywalls, access controls, or site terms.

Input Schema

TableJSON Schema

Name	Required	Description
`job_key`	Yes	job_key identifies a research session. Reuse it with a new objective to run a follow-up iteration that references the session's prior results (each iteration is a separate paid job); an identical request retries idempotently. Sessions are referenceable for 7 days, then results are cleared.
`objective`	Yes
`targetUrl`	No	Optional public HTTPS focus hint; when omitted the service plans up to 5 public start URLs from the objective and binds them into the quote.
`notify_email`	No	Optional: email the completed report to this address from a9n9@agentmail.to. Delivery preference only; not part of the payment-bound request hash.
`payer_address`	No	Optional Tempo payer address for loyalty pricing: 10% off after $2.00 of reconciliation-confirmed on-chain spend from that address. Settlement must then come from it.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`error`	No
`result`	No
`status`	Yes
`quoteId`	No
`createdAt`	No
`statusUrl`	No
`trackerCode`	Yes
`progressStage`	Yes
`progressPercent`	Yes
`requestBodyHash`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedAug 19, 2026

changedInput schema / properties / job_key / description

Previous value: -"Caller-generated unique key for one intended job; reuse only for retries."New value: +"job_key identifies a research session. Reuse it with a new objective to run a follow-up iteration that references the session's prior results (each iteration is a separate paid job); an identical request retries idempotently. Sessions are referenceable for 7 days, then results are cleared."

Changed1 schema field changedAug 18, 2026

addedInput schema / properties / payer_address

Added value: +{
+  "description": "Optional Tempo payer address for loyalty pricing: 10% off after $2.00 of reconciliation-confirmed on-chain spend from that address. Settlement must then come from it.",
+  "pattern": "^0x[a-fA-F0-9]{40}$",
+  "type": "string"
+}

First observedAug 18, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description discloses key behaviors: it is 'paid' and 'bounded', uses a 'real remotely hosted Browserbase session', and explicitly states limitations: 'The service does not bypass CAPTCHAs, logins, paywalls, access controls, or site terms.' It also mentions session persistence ('Sessions are referenceable for 7 days') and idempotency ('identical request retries idempotently' in the schema). These details go beyond annotations and provide full transparency.

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 a single focused paragraph that packs essential details—purpose, limitations, usage hint, and parameter nuance—without redundant elaboration. It is appropriately sized for a complex tool, balancing completeness with brevity.

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?

The description covers limitations, usage, and session behavior, but does not describe the tool's return value (what the client receives after starting research). Given that an output schema exists (has_output_schema: true), this gap is acceptable, but it slightly reduces completeness for a self-contained understanding.

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?

The schema already includes descriptions for each parameter, and the tool description adds extra meaning for targetUrl: 'without it the quoted plan of public start URLs derived from the objective is executed.' It also clarifies job_key's role in reuse and idempotency. However, the description does not independently explain 'objective' or 'payer_address' beyond what the schema provides, so it only partially adds value.

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 clearly states the tool's function: 'Start bounded paid research...' and distinguishes it from sibling tools like quick_search, research_quote, and status. The verb 'Start' and specific resource 'paid deep research' make the purpose unambiguous.

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?

The description provides a direct usage hint: 'Call a9n9_research_quote first when price visibility is needed.' It also implies the tool is for initiating research after planning, and mentions the optional targetUrl. However, it doesn't explicitly state when to use this tool over others for all scenarios, leaving some ambiguity.

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

All a9n9 Deep Research tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0

Disambiguation5/5

Each tool has a distinct role: quick_search is the free tier, while research_quote, research_start, research_status, and research_submit_payment form a clear paid workflow. No two tools could be plausibly confused.

Naming Consistency4/5

All tools share the a9n9_ prefix and snake_case convention. Minor inconsistency exists because quick_search breaks the research_* pattern used by the other four tools, but the verb/noun usage is otherwise predictable.

Tool Count5/5

Five tools is well-scoped for a research service: one free entry point and four lifecycle steps (quote, start, payment, status). Each tool serves a necessary and non-redundant function.

Completeness4/5

The core deep-research workflow is fully covered: free quick search, quote, paid start, payment submission, and status/result retrieval. Minor gaps like cancellation or job listing are absent but not essential to the primary purpose.

Resources

Need Help?