delete_persona

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states the action without disclosing behavioral traits: whether deletion is permanent, cascading (does it delete associated relationships/custom entries?), requires authentication, or is reversible. For a destructive operation with zero annotation coverage, this is a significant gap.

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 maximally concise at a single short phrase, but this veers into under-specification rather than effective conciseness. It is appropriately front-loaded but fails to earn its value by adding anything beyond the tool name itself.

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?

This is a destructive operation with no annotations and no output schema. The description should explain deletion semantics, permanence, cascading effects on related data (relationships, custom entries, tags), and any prerequisites. With only 'delete persona' stated, the description is inadequate for an agent to safely use this tool. The single ambiguous 'entry ID' parameter adds to the incompleteness.

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 schema has 100% coverage with a single 'id' parameter described as 'エントリID (UUID)' (entry ID, UUID). The description adds no parameter-level information beyond the schema, but since coverage is complete, the baseline of 3 is appropriate. The lack of context about what kind of entry ID this is (persona-specific, or general entry ID) is a minor gap.

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 'ペルソナを削除' (Delete persona) states the core action of deleting a persona, but it is essentially a restatement of the tool name 'delete_persona'. It provides no additional clarity about what a persona is, what deletion implies, or what distinguishes this from related tools like delete_profile, delete_custom_entry, or delete_values_philosophy.

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 to use this tool versus alternatives. While sibling tools like delete_goal, delete_skill, and other delete_* tools suggest a per-resource deletion pattern, the description gives no context about when personas should be deleted versus profiles, custom entries, or other related resources. No exclusions or prerequisites are mentioned.

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