CPersona

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

Beyond annotations declaring destructiveness and idempotency, the description adds critical context about exactly which data categories are destroyed (memories, profiles, episodes) and indicates authorization level through 'used by kernel.' It could be strengthened by explicitly confirming irreversibility or describing idempotent behavior in the text itself.

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 sentences efficiently deliver the core functionality (comprehensive deletion), scope enumeration (three data types), and usage context (kernel operation) with zero redundancy. The critical scope qualifier 'ALL' appears immediately, front-loading the most important distinction.

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, irreversible operation with no output schema, the description adequately specifies the wipe scope and authorization context. It appropriately relies on the destructiveHint annotation for safety signaling, though explicitly stating irreversibility or success indicators in the text would provide additional value.

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?

With 100% schema description coverage for the single agent_id parameter ('Agent ID whose data should be purged'), the schema fully documents input requirements. The description provides no additional parameter semantics or format guidance, which is acceptable given the schema's completeness.

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 specifies the exact verb (Delete), resource (ALL data), and enumerates affected categories (memories, profiles, episodes). It clearly distinguishes this comprehensive wipe from sibling tools like delete_episode or delete_memory by emphasizing complete agent data removal across all types.

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 phrase 'Used by kernel during agent deletion' provides explicit operational context indicating this is for comprehensive agent lifecycle cleanup rather than routine data management. While it establishes privileged usage context, it does not explicitly name partial-deletion alternatives like delete_episode for non-comprehensive scenarios.

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