Skip to main content
Glama

Start a full evidence review

start_ultradeep

Use this when the user asks for a full review of the evidence on a research question in aging or longevity, beyond a short answer. Not for personal medical advice, doses or symptoms. Writes over several minutes a review in five sections: the bottom line, the evidence by kind of study, contradictions and gaps, how far it has got toward patients, what would change the answer. Counts against the user's Ultradeep reviews. Returns at once with the conversation's address and a question_id for get_ask_answer.

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": {
      "question": "<question>"
    },
    "name": "start_ultradeep"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionYesThe research question in the user's words, in any language; the answer is written in the question's language.
conversation_idNoTo ask a follow-up in a conversation this tool or ask_arn started: its `conversation.id`. Leave out to start a new conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial context the annotations cannot carry: it is asynchronous ('returns at once with the conversation's address and a question_id'), slow ('writes over several minutes'), and metered ('counts against the user's Ultradeep reviews'). It also outlines the five-section output, so the agent knows what will be produced and how to retrieve it.

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-loads the trigger condition and keeps every subsequent sentence informative (exclusion, cost, latency, return shape). The five-section enumeration is a bit dense but each item conveys real output structure rather than filler.

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?

There is no output schema, and the description compensates by explaining the immediate return value (conversation id plus question_id) and pointing to get_ask_answer for the result. With cost, latency, and exclusions all covered, an agent has everything needed to decide and call correctly.

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 coverage is 100%, so question, language behavior, and conversation_id are already fully documented in the schema. The description adds no syntax or format detail about either parameter, so it sits at baseline.

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 ('full review of the evidence on a research question in aging or longevity') and scopes it against a shorter answer, which is enough to separate it from ask_arn and the list/search siblings. The verb-noun pairing is 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?

Gives an explicit trigger ('when the user asks for a full review... beyond a short answer') and an explicit exclusion ('Not for personal medical advice, doses or symptoms'). It stops short of naming ask_arn as the fallback for a short answer, leaving that alternative implied rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.