Skip to main content
Glama

Ask Lil Nerdy

lil_nerdy_ask_question
Destructive

Ask Lil Nerdy, Nerd/Noir's own assistant, and get its answer with the collection pages it drew on. Use it when the user asks for Lil Nerdy, or for Nerd/Noir's judgment on their situation; for a plain lookup, search the collection yourself. It knows the reader's saved memories, and for a reader with workshop access it can cite that workshop's slides. Each call is a new conversation: pass only the earlier turns with Lil Nerdy that the question depends on, as history. Pass document_id to ask about one of their builder documents; with edit allowed, it can change that document. Each call counts against the reader's chat allowance on nerdnoir.ai and can take 20 to 60 seconds.

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": "lil_nerdy_ask_question"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoA collection slug the question is about, for example "concepts/teaming/conways-law".
historyNoEarlier turns of this thread with Lil Nerdy, oldest first, at most 10.
questionYesThe question, in the user’s words.
document_idNoOne of the user’s builder documents, from tools_list_documents.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint=true, openWorldHint=false) it discloses the traits that actually matter: each call is a stateless new conversation requiring explicit history, a call with edit permission can mutate a builder document, each call consumes the reader's chat allowance, and latency is 20-60 seconds. Nothing here contradicts the annotations; the mutation warning is consistent with destructiveHint=true.

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?

The identity and primary trigger are front-loaded, followed by routing, scoping, and cost information, with no filler sentences. It is dense and slightly packed in the middle clauses, but every sentence carries distinct information an agent needs before calling.

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?

Although there is no output schema, the description explains the return shape (an answer plus the collection pages it drew on) and the citation scope (reader memories, workshop slides for readers with workshop access). For a costly, potentially mutating, stateless tool it covers cost, latency, statefulness, and side effects.

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 all four parameters, but the description adds real meaning on top: history should contain only the earlier turns the question depends on, and document_id changes behavior (it can edit the document when edit is allowed) rather than merely naming the field. The page parameter's purpose is stated less precisely than the others.

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 names a specific verb and resource ("Ask Lil Nerdy ... get its answer with the collection pages it drew on") and explicitly separates it from the sibling search surface by saying "for a plain lookup, search the collection yourself." An agent can distinguish this assistant tool from search_collection 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?

It gives an explicit trigger ("when the user asks for Lil Nerdy, or for Nerd/Noir's judgment on their situation") and an explicit exclusion routing to the alternative ("for a plain lookup, search the collection yourself"). It also states the conditional path for document_id and edit permission, so the when-to-use decision is fully specified.

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.

Resources