Ask an investment question to get a RAG-augmented answer with citations from InvestBrain's knowledge base.
Ask an investment question and get RAG-augmented answer.
Args:
question: Investment question (e.g., "什么是护城河？")
Returns:
dict: Answer with source citations from master knowledge base
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose that the response is a dict with source citations drawn from a 'master knowledge base', which is useful output context absent an output schema, but says nothing about scope, latency, auth, or how it handles unanswerable questions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Short and front-loaded, with the core action in the first sentence. The Args/Returns boilerplate is slightly redundant but not wasteful for a single-parameter tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter, no-annotation, no-output-schema tool, the description covers purpose, the input, and the return shape. It is still incomplete on the key decision an agent faces: when to use this Q&A tool versus the other rag_* search tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
One parameter at 0% schema description coverage, so the description must compensate. It names the parameter and gives a concrete natural-language example ('什么是护城河？'), which usefully signals free-text phrasing rather than a keyword or ID, but adds little beyond that.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a clear verb (ask) and resource (investment question) and specifies the output is a RAG-augmented answer with source citations. However, it never distinguishes itself from close siblings like rag_search_knowledge, rag_rag_search_reports, or rag_get_master_view, which an agent must choose between.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. The only signal is the implied 'investment question' framing, which does not tell the agent how this differs from the other rag_* retrieval tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.