clear_index

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

Beyond the destructiveHint annotation, the description discloses that the operation is irreversible, deletes all indexed metadata and search history, and specifically excludes in-memory caches. It also instructs the necessary follow-up action (sync_emails), providing full transparency about consequences.

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 four tightly written sentences, each earning its place: what, when, how to recover, and what it does not do. It is front-loaded with the core action and avoids any fluff.

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?

Given that this is a destructive irreversible action with no output schema, the description fully addresses the agent's needs: what exactly is deleted, under what circumstances to invoke, the irreversibility, and the required rebuild step. The sibling clear_cache is explicitly differentiated, leaving no ambiguity.

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 takes zero parameters, so there is no parameter schema to elaborate on. The description nevertheless clarifies what the tool operates on (persistent SQLite index) and the irreversibility, which is sufficient for an agent to invoke without additional parameter context. Baseline 4 per rubric for zero-param tools.

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 a specific verb and resource: 'Delete the entire persistent SQLite mailbox index from disk.' It clearly distinguishes the tool from sibling clear_cache by stating the scope is the persistent index, not in-memory caches.

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 explicitly states when to use it ('reset a corrupted or schema-incompatible index') and provides alternatives: after clearing, call sync_emails to rebuild, and for in-memory caches use clear_cache. This is explicit when-to-use and when-not-to-use guidance.

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