Skip to main content
Glama

Answer doctrine questions

mcai_answer
Read-onlyIdempotent

Answers natural-language questions about Meta-Consciousness Theory with definitions, source quotations, related concepts, and citations; returns type=none when no coverage exists.

Instructions

Answer full-sentence questions about the Meta-Consciousness Theory, returning authoritative definitions, source quotations, and related concepts. Use when the user asks in natural language and does not need one specific entry, e.g. "What is meta-consciousness?", "How are meta-recognition and meta-knowledge related?", "How does the progenerative agent explain AI emergence?". Returns JSON with question, type (concept / faq / none), answer and citations; type='none' means the base does not cover it, so call mcai_search before saying it is unknown. Routing: for a known term and its full entry (aliases, sources, citations, relations) use mcai_concept; if unsure of the exact term use mcai_search; for a catalog use mcai_list; for relations only use mcai_related. Boundary: answers come only from this knowledge base; unlisted concepts return type=none. Do not extrapolate, complete, or introduce meanings outside the corpus.

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": "mcai_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNofull returns the answer with citations; citations returns only the source citations for the answer, for RAG or audit use.full
questionYesA complete natural-language question, ideally 5–120 characters, one question per call; Chinese or English is fine. Include the exact term when possible, e.g. "什么是元意识" or "元灵和元子有什么区别".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.6
    • addedInput schema / properties / format
      Added value: +{
      +  "default": "full",
      +  "description": "full returns the answer with citations; citations returns only the source citations for the answer, for RAG or audit use.",
      +  "enum": [
      +    "full",
      +    "citations"
      +  ],
      +  "type": "string"
      +}
  2. Changed1 schema field changedv0.1.5
    • changedInput schema / properties / question / description
      Previous value: -"一个完整的自然语言问题,建议 5–120 字,一次只问一个问题;中英文均可。建议包含明确的术语,例如“什么是元意识”“元灵和元子有什么区别”。"New value: +"A complete natural-language question, ideally 5–120 characters, one question per call; Chinese or English is fine. Include the exact term when possible, e.g. \"什么是元意识\" or \"元灵和元子有什么区别\"."
  3. Changed2 schema fields changedv0.1.2
    • changedInput schema / properties / question / description
      Previous value: -"要回答的问题,中英文均可,例如“什么是元意识”“元灵和元子有什么区别”"New value: +"一个完整的自然语言问题,建议 5–120 字,一次只问一个问题;中英文均可。建议包含明确的术语,例如“什么是元意识”“元灵和元子有什么区别”。"
    • addedInput schema / properties / question / examples
      Added value: +[
      +  "什么是元意识",
      +  "元灵和元子有什么区别"
      +]
  4. Changed2 schema fields changedv0.1.1
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / question / description
      Previous value: -"用户问题,中英文均可"New value: +"要回答的问题,中英文均可,例如“什么是元意识”“元灵和元子有什么区别”"
  5. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the baseline burden is light; the description nonetheless adds real behavior: the JSON return shape (question/type/answer/citations), the meaning of type='none', the requirement to try mcai_search before reporting a gap, and the closed-corpus boundary with an explicit anti-extrapolation instruction. These are operational traits the annotations cannot express.

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 purpose and examples, then a clearly labeled routing block and boundary block. Every sentence is functional, but the routing enumeration is dense and repeats sibling names already visible in the tool list, costing a little economy.

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?

No output schema exists, yet the description specifies the return fields and the type discriminator, defines the none case, and states the corpus boundary. Combined with 100% schema coverage, an agent has everything needed to call it correctly and interpret the response.

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% and the question parameter even carries examples and a length hint in the schema, so the description does not need to re-document inputs. It does not mention the 'format' enum (full vs citations) at all beyond the citations mentioned in the return shape, so it adds no meaning beyond the structured fields. Baseline 3 applies.

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 ('Answer full-sentence questions about the Meta-Consciousness Theory') and immediately enumerates what an answer contains: definitions, source quotations, related concepts. Three concrete example questions make the scope unambiguous, and the routing paragraph differentiates it from mcai_concept, mcai_search, mcai_list, and mcai_related by name.

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?

Explicit trigger condition ('user asks in natural language and does not need one specific entry') plus a full routing block assigning each sibling a role: mcai_concept for a known term's full entry, mcai_search when the term is uncertain, mcai_list for a catalog, mcai_related for relations. It also states the fallback behavior when type='none' (call mcai_search before declaring unknown), so both when-to-use and when-not-to-use are covered.

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