create_episode

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

No annotations are provided (no readOnlyHint, destructiveHint), so the description carries the full burden of behavioral disclosure. The description says only 'create new episode' — it does not disclose that this is a mutation, whether it requires authentication/profile binding, whether it appends to a profile's collection, or what validation occurs on the type enum values. For a write operation with zero annotations, 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 one short sentence in Japanese, which is appropriately brief. But it's arguably under-specified rather than concise — the single phrase 'create new episode' provides minimal value and could have been expanded to cover the STAR structure and data model without becoming verbose. It's efficient but under-informative.

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 moderately complex tool: nested objects, 15+ fields, a type enum, profile-scoped vs account-scoped key handling, and no output schema. Given this complexity and no annotations, the one-sentence description is inadequate. It doesn't explain the episode data model (STAR framework), the type taxonomy, how episodes relate to profiles, or how success/failure validation might work. Compared to sibling tools like create_achievement or create_life_event, the description fails to position this tool within the broader domain.

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 50% description coverage. The description itself provides zero parameter information. However, the schema descriptions are reasonably rich in Japanese (e.g., type enum values, STAR field labels, confidence/importance ranges). The description doesn't add anything beyond the schema, and the profile_id guidance about key scoping is already in the schema. There's a partial gap for the ~50% of fields lacking schema descriptions (mention_tone, metadata, period fields have short/absent descriptions).

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 'エピソードを新規作成' (create new episode) clearly states the verb+resource action. However, it doesn't clarify what an 'episode' is in this context (STAR framework, career/professional narrative entries), nor does it distinguish from sibling tools like update_episode or delete_episode beyond the obvious create/update/delete distinction. The schema reveals STAR fields (situation/task/action/result), so a hint about this structure would add value.

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?

No guidance is provided on when to use this tool versus alternatives. There are many sibling create_* tools (create_skill, create_project, create_achievement, create_career_entry, etc.), and the description gives no differentiation between what constitutes an 'episode' versus a 'life_event', 'career_entry', or 'achievement'. The schema's profile_id description offers some context on key scoping, but that's structured data, not usage guidance.

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