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

With no annotations, the description carries the full burden and does disclose the two most important traits for a destructive operation: exactly what is removed (personal session items) and what survives (static system invariants, other users' items). It omits reversibility/recovery and any auth or confirmation requirements.

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, front-loaded with the operation class, and every clause adds information (what is cleared, what is kept). No filler.

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 destructive tool with zero annotation coverage and no output schema, the description covers blast radius but not irreversibility, required privileges, or what the call returns. Adequate to select the tool, thin on what happens after invocation.

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%, so both parameters are already documented in structured fields. The description only loosely gestures at them ('your personal session items', 'system invariants preserved') without explaining ownerId namespace scoping or the effect of setting preserveBasePolicies to false.

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?

States a specific verb (clears) and a precisely scoped resource (personal session items in the KV Prompt Cache), plus the [PUBLIC WRITE] tag signals the operation class. It implicitly separates itself from siblings like get_kv_cache_item/put_kv_cache_item by scope, though it never names them.

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 preservation clause hints at when this is appropriate (you want to clear session state without disturbing invariants), but there is no explicit when-to-call, no mention of related tools, and no stated preconditions or confirmation step.

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