maintenance_repair

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It explicitly reveals the destructive nature of the repair (corrupted tables are dropped and recreated) and the need for subsequent re-indexing. However, it omits details such as whether data is preserved or if user confirmation is required, but the drop/recreate statement is a strong disclosure.

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 description is three short sentences, each adding essential information: the core action, the specific repair method (drop/recreate), and a required follow-up (index rebuild). There is no redundancy or filler, and the most important verb appears first.

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 tool with no parameters and no output schema, the description covers the essential context: what it does, how it does it, and what to do after. It could be more explicit about preconditions (e.g., 'use when corruption is suspected') but the stated behavior makes this clear enough. The mention of re-indexing connects to sibling tools like index_status implicitly.

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?

The tool has zero parameters, so the schema provides no information. Per the rubric, a baseline of 4 applies when there are no parameters, and the description does not need to elaborate further. The absence of parameters is consistent with a simple trigger-style maintenance tool.

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 clearly states the tool's function: detecting corruption in LanceDB tables and automatically repairing them. It specifies the resource (LanceDB tables) and the verbs (detect, repair), and the mention of 'drop→再作成' makes the operation distinct from sibling tools like search or index_status.

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 description implies when to use the tool: when corruption is detected, and it provides a clear post-condition by stating that re-indexing is required after repair. It does not explicitly name alternatives or exclusions, but the context is unambiguous enough for a maintenance tool.

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