Search a static analysis graph by literal keywords and paginate results, or use a node ID to read a full node and its coverage limits; nodes are static, not runtime behavior.
按字面关键词搜索完整静态分析图并分页；query 不是语义搜索。指定 node_id 可读取完整节点及覆盖限制。节点不等于实际运行行为。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | Yes | ||
| query | Yes | ||
| offset | Yes | ||
| node_id | No | ||
| study_id | Yes | 研究 ID，由 research_create 返回 | |
| analysis_id | Yes |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish a safe read (readOnlyHint=true, destructiveHint=false). The description adds real behavioral context beyond them: literal vs semantic matching, that specifying node_id returns a full node with coverage limits, and that nodes do not represent actual runtime behavior. That runtime caveat is a genuine disclosure not captured by the annotations.
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?
Three tight clauses, front-loaded with the primary search behavior before the node_id alternate path and the runtime caveat. Every sentence carries information; no filler.
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 6-parameter tool with 17% schema coverage and no output schema, the description covers the two most semantically loaded parameters but leaves pagination bounds and analysis_id unexplained, and offers nothing about result shape. Adequate but with visible gaps.
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 description coverage is only 17%, so the description bears most of the load. It adds useful meaning for query (literal keyword, not semantic) and node_id (reads full node plus coverage limits), but offset, limit, and analysis_id are left entirely undocumented. Partial compensation for a low-coverage schema.
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 (literal keyword search) and resource (complete static analysis graph) with pagination, and carves out a distinct node_id read mode. The clarification that query is not semantic search sharpens the purpose well. It stops short of naming which sibling to prefer for non-keyword lookups, so it doesn't fully differentiate within the crowded research_* family.
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?
The explicit 'query is not semantic search' and the node_id branch imply when each mode applies, but there is no clear 'use X instead' routing against siblings like research_analyze or research_read_source. Usage is implied rather than spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.