mcp-server

Deep Research

alterlab_research

Get a cited report or structured JSON for a hard question: a budgeted research job plans searches, reads many sources, follows leads and attaches a citation to every claim. Use when one search is not enough; for a quick lookup use alterlab_search. Cost: platform spend never exceeds max_cost_microcents; it runs on your own LLM key (BYOK) and without one it returns byok_key_required and charges nothing. Set effort (lite, standard, deep, exhaustive) to trade depth for spend. The call waits within the tool time budget; if the job is still running it returns the job id and status, and you call again with job_id to fetch it. Returns status, cost, coverage, warnings and the result.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "alterlab_research"
  }
}

Input Schema

Name	Required	Description
`model`	No	BYOK model override.
`query`	No	Research question. Required unless job_id is given.
`effort`	No	Search and reading budget tier. Default: standard.
`job_id`	No	Fetch an existing research job instead of starting one.
`output`	No	Structured answer, markdown report with inline citations, or both. Default: json.
`sources`	No	Source controls: include/exclude domains, categories, seed_urls, only-these-URLs.
`criteria`	No	Rules the result must meet; each is reported as met or unmet.
`provider`	No	BYOK provider for planning and synthesis.
`max_depth`	No	Max follow-up rounds.
`max_sources`	No	Max sources read.
`min_sources`	No	Independent sources required per field.
`output_schema`	No	JSON Schema for the structured answer; each filled field carries citations.
`max_cost_microcents`	No	Hard cap on platform spend in microcents (1,000,000 = $1.00).

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations only say non-read-only, open-world, non-idempotent, non-destructive; the description goes well past that by disclosing the spend model (hard cap via max_cost_microcents), the BYOK dependency and the byok_key_required failure that charges nothing, and the timeout/polling contract. It is candid about cost and partial-result behavior, though it does not say whether a repeated call with the same query re-bills or deduplicates.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the deliverable, then usage, then cost, then the async contract — a sensible order with no filler sentences. It is a dense run-on that packs cost, BYOK, effort and polling into one block, which costs some skimmability.

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 13-parameter async tool with no output schema, the description supplies what structured fields cannot: the return payload (status, cost, coverage, warnings, result), the polling loop, and the spend/authentication failure modes. An agent can call it correctly and handle its responses without further documentation.

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 baseline is 3, but the description adds real meaning: effort as a depth-versus-spend trade, criteria results reported as met or unmet, and output_schema fields carrying citations. The nested sources object is still described only generically, matching the schema rather than expanding on it.

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 deliverable — 'Get a cited report or structured JSON for a hard question' — and immediately scopes it as a multi-source, budgeted research job. The distinction from simple retrieval is explicit and an agent can tell it apart from alterlab_search without opening either schema.

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 the exact selection rule: 'Use when one search is not enough; for a quick lookup use alterlab_search.' It also tells the agent how to continue a run ('call again with job_id to fetch it') and which knob trades cost against depth.

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

All mcp-server 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.