Repair the project memory index in batches. Pass full=true to verify and fix all valid records, then continue using the next_cursor until it returns empty and retry if pending remains.
分批修复索引；full=true 对全部有效记录核对补齐（仅所有者）。继续传 next_cursor，直到为空；pending 非零需重试。
| Name | Required | Description | Default |
|---|---|---|---|
| full | No | ||
| limit | No | ||
| cursor | No | ||
| directory | Yes |
Changes observed during successful MCP inspections.
v0.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses the full-mode scope ('仅所有者'), pagination behavior (continue with next_cursor until empty), and the retry condition (pending nonzero), which are meaningful operational traits beyond a simple action label.
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?
The entire description is one dense, front-loaded sentence with no filler. It states the core action first, then packs mode semantics, ownership restrictions, and retry behavior into a compact set of clauses.
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?
The description gives enough operational guidance to attempt a call (cursor looping, retry condition, full mode), but with no output schema it does not clearly define the response structure. It also leaves directory and limit semantics implicit, making the tool somewhat incomplete for a fully informed agent.
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 0%, so the description must compensate. It adds meaning for cursor and full, and implies response fields like next_cursor and pending, but it does not explain directory or limit. The compensation is partial, leaving two parameters without meaningful context.
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?
The description opens with '分批修复索引' (batch repair index), giving a specific verb + resource. It clearly identifies the tool's core function, though it does not explicitly differentiate it from sibling memory tools.
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?
Usage is implied through operational instructions: use full=true for full checks, pass next_cursor until empty, and retry when pending is nonzero. However, there is no explicit statement of when to choose this tool over alternatives like memory_rebase or memory_preview.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.