prune_index

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

With no annotations, the description carries the full burden and does well: it discloses the destructive operations (drops orphan chunks) and that force deletes and rebuilds the entire collection from scratch. It stops short of stating irreversibility, expected runtime, or whether the index is unavailable during the rebuild.

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?

Two tight sentences with no filler; the default behavior is stated first and the escalated destructive mode second, which matches how an agent would evaluate risk.

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?

An output schema exists so return values need not be explained, and the core behavior is covered. What is missing for a destructive maintenance tool with zero annotations is the safety envelope: irreversibility, cost/duration, and how it relates to sibling index and maintenance tools.

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 0% for the single `force` parameter, so the description must compensate and does: it explains that force=True deletes and rebuilds the entire collection rather than pruning in place. The default false is left implicit, but the semantic consequence of the flag is clear.

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 names a specific verb and resource ('prunes the vector index') and enumerates the concrete operations (drop orphan chunks, VACUUM, optional full rebuild). An agent knows exactly what the tool does, though it never contrasts itself with index_codebase or maintenance_run, which also touch the index.

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?

There is no guidance on when pruning is warranted versus rebuilding via index_codebase or running maintenance_run. The only conditional offered is what force does, not when to reach for this tool or when to avoid it.

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