crowdsmart-mcp

Overview Schema Source Related Servers Discussions Admin

ask_knowledge_agent

Ask a Knowledge Agent a question to get answers grounded in its documents, with citations and optional word-for-word passages. Use it when you need sourced responses or to verify document coverage.

Instructions

Ask a Knowledge Agent a question and get an answer from its documents, with citations.

Generative mode writes an answer. A sentence ending in a citation such as [1] is evidence: it was checked against passage 1, or is shown in the passage's exact words. A sentence without a citation is the agent's own reasoning. Referenced mode returns the cited passages word for word, with no model writing. When the documents do not cover the question, the agent says so.

"confidence" is CrowdSmart's retrieval score, from 0 to 1: how well the best passages match the question. It does not show whether the answer is right. "generation_source" says how the answer was produced (for example "corpus_extractive" or "abstained"). "knowledge_source" is "documents" unless general-knowledge backfill contributed. CrowdSmart records each question in the agent's query history.

Args: agent_id: Knowledge Agent ID, from list_knowledge_agents. question: The question to answer from the agent's documents. mode: "generative" or "referenced". Omit to use the agent's own setting. max_chunks: Number of passages to retrieve (default 5).

Input Schema

Name	Required	Description	Default
`mode`	No
`agent_id`	Yes
`question`	Yes
`max_chunks`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 30, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds substantial context beyond the thin annotations: it explains what a citation means (checked evidence vs agent reasoning), that referenced mode returns verbatim passages with no model writing, and importantly that each question is recorded in the agent's query history — which is exactly why readOnlyHint is false despite this being a questioning tool. It also warns that 'confidence' is a retrieval score, not a correctness signal.

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, then the interpretive field notes, then Args — a sensible order with little padding. It runs long and restates defaults already present in the schema, but nearly every sentence carries decision-relevant meaning.

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 4-parameter tool with an output schema, an empty schema description, and minimal annotations, this covers everything an agent needs: mode selection, how to interpret the returned answer and accompanying fields, and the query-history side effect. Nothing material is left to guess.

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 description coverage is 0%, so the description carries the full burden and does so for all four parameters, including where agent_id comes from (list_knowledge_agents), the mode enum values plus the omit-to-use-agent-default behavior, and max_chunks' default of 5. Only the agent_id pattern constraint and any bounds on max_chunks are left unstated.

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?

Opens with a specific verb+resource+output: 'Ask a Knowledge Agent a question and get an answer from its documents, with citations.' This is clearly distinct from siblings like list_knowledge_agents (enumeration) or read_document (raw document retrieval).

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 explicit guidance for the generative vs referenced mode choice and states the abstention behavior when documents don't cover the question. It does not, however, say when to reach for this tool versus read_document or check_corpus_quality on the same data, so the sibling routing is only implied.

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