AstraEye Labs

Create a research project

create_research_project

Creates a research project from analyses (analysisIds from list_analyses) or a template (templateId from list_templates), covering what covers says. It only creates: nothing is priced, run or spent. To run it, price it with quote_research_run (its projectId). Assets must already be on the watchlist (add_to_watchlist). Report options and a description are optional.

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": {
      "title": "<title>",
      "covers": "<covers>"
    },
    "name": "create_research_project"
  }
}

Input Schema

Name	Required	Description
`title`	Yes	The project's name.
`covers`	Yes	What it covers: chosen_assets (assetIds), the watchlist, holdings_or_watchlist, or global_market (marketSliceIds, skipsAssetClass).
`assetIds`	No	With covers chosen_assets: the assets, by assetId. From find_assets or list_watchlist; at most 25.
`templateId`	No	A template id from list_templates (or analysisIds instead).
`analysisIds`	No	The analyses to run, by id (or a templateId instead). From list_analyses.
`description`	No	Optional description, saved exactly as given.
`marketSliceIds`	No	With covers global_market: at most one slice id per asset class.
`clientRequestId`	No	Optional UUID you generate for this request. Retrying with the same id never does it twice.
`reportOptionsOn`	No	Report options to turn on. methodology, audio_methodology, quiz, visual_brief, audio, questions.
`skipsAssetClass`	No	With covers global_market: the class left out (crypto for Stocks only).

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 1, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false and idempotentHint=false. The description adds useful behavioral context beyond that: creation only, no pricing/running/spending, and that assets must be watchlisted first. Idempotency via clientRequestId is left to the schema.

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?

Front-loaded with the core action, then prerequisites and next steps, all in four tight sentences. Minor awkwardness in 'covering what covers says' but no wasted sentences.

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?

Covers prerequisites, parameter relationships, and downstream sequencing well for a 10-parameter mutation with no output schema. It does not explicitly say what the call returns (presumably a projectId) or address report-option interactions, leaving a small gap.

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?

Schema coverage is 100%, so the schema already documents each field. The description still adds meaning by relating parameters: analysisIds vs templateId as alternatives, and covers values mapping to assetIds vs marketSliceIds/skipsAssetClass.

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?

States a specific verb and resource ('Creates a research project') and immediately scopes the inputs (analyses or template) plus the coverage semantics. The clause 'It only creates: nothing is priced, run or spent' cleanly separates it from quote_research_run and start_research_run.

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?

Gives explicit sequencing ('To run it, price it with quote_research_run (its projectId)') and a prerequisite ('Assets must already be on the watchlist (add_to_watchlist)'), and names the source tools for analysisIds and templateId.

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

All AstraEye Labs tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?