reindex_all

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

No annotations are provided, so the description carries full burden. It explicitly discloses destructive behavior: 'Delete existing chunks' and 'slow, destructive operation.' This goes beyond vague warnings and gives concrete behavioral details, making the tool's impact transparent.

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 two sentences: the first states the action and method, the second covers use cases and a warning with an alternative. Every phrase adds value, and the destructive nature is front-loaded.

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 the operation is destructive and potentially slow, the description covers what it does, when to use it, why, the alternative, and a warning. No output schema is present, but the core selection and invocation context is fully addressed, making it complete for an 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 coverage is 100% and the only parameter optimizeAfter already has a clear description in its schema. The tool description does not add parameter-level context, so the baseline of 3 applies.

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 opening line 'Re-ingest ALL indexed files from scratch' states a specific verb and resource, and the description explicitly contrasts with reindex_stale ('prefer reindex_stale for routine updates'), distinguishing it from sibling tools. It clearly names the operation and scope.

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 gives explicit when-to-use conditions ('after changing the embedding model, chunker parameters, or when the index is corrupted') and provides a direct alternative with an exclusion ('prefer reindex_stale for routine updates'). This is exactly the guidance needed for selection.

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