Search historical investment thoughts and memories in InvestBrain via semantic query to retrieve relevant thought cards, ranked by relevance.
Search user's historical thoughts and memories using semantic search.
Args:
query: Search query (e.g., "茅台", "上次关于苹果的想法")
Returns:
list: Matching thought cards, sorted by relevance
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose two useful traits: retrieval is semantic (not keyword) and results are sorted by relevance. It omits pagination, result-count limits, and any auth or scope constraints.
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?
Front-loaded purpose sentence followed by short Args/Returns blocks; every line carries information. The Args/Returns scaffolding is slightly heavier than needed for one parameter but is not wasteful.
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 single-parameter read tool with no output schema, the description usefully explains the return shape (matching thought cards sorted by relevance), which compensates for the missing output schema. It is still thin on result volume and pagination behavior, leaving a small gap.
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?
Schema coverage is 0% and the single 'query' property has no description, so the description must compensate. It supplies the parameter name plus two illustrative queries ('茅台', '上次关于苹果的想法'), which conveys that natural-language or mixed-language input is expected, but adds no syntax or length guidance.
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 specific verb and resource: searching the user's historical thoughts and memories, with the retrieval mode (semantic search) named. It is distinguishable from list-style siblings like thought_get_thought_cards, though it does not name any sibling explicitly.
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?
No guidance on when to prefer this over the many adjacent tools (thought_get_thought_cards, rag_search_knowledge, memory_get_behavior_patterns). The example queries imply it is for fuzzy recall, but the agent is left to infer the routing decision.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.