repair_index

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

Description contradicts annotations: annotations set readOnlyHint=true and destructiveHint=false, but description states 'DESTRUCTIVE' and describes mutations (drop orphans, drop vector store, rebuild FTS). This is a clear annotation contradiction, scoring 1 per instructions.

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?

Concise and front-loaded. Three sentences pack all essential info: purpose, modes, transactional guarantee, prerequisite recommendation, return format. No unnecessary words.

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?

Despite no output schema, the description fully covers the tool's behavior: modes, transactional safety, destructive nature, and return structure (JSON with mode, ok, detail, affected). Completely informs an agent how to invoke and interpret results.

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 single 'mode' parameter has 100% schema coverage with enums. The description adds high value by explaining each mode's purpose and consequences (e.g., drop-vec forces re-embed, rebuild-fts refreshes FTS5). This goes well beyond the schema's minimal descriptions.

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?

Description clearly states 'Apply a targeted repair to the local SQLite index' with three specific modes (drop-orphans, drop-vec, rebuild-fts). It distinguishes from siblings like verify_index and embed_repo by recommending verify_index first and explaining each mode's effect.

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?

Explicitly tells when to use each mode and advises 'verify_index first to find out which mode is needed'. Also warns 'DESTRUCTIVE' and notes transaction safety, providing clear context for usage.

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