claude_turn

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

With no annotations provided, the description carries the full burden. It usefully discloses that results are returned as structured statuses without parsing human-facing error strings, and that no observer-specific logic is included. However, it does not disclose potential side effects of issuing or recovering operations, authentication needs, or whether operations are idempotent or reversible.

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 a single dense sentence that front-loads the core purpose and then adds behavioral details. It avoids filler, though the heavy Japanese jargon ('aiterm相関付き', 'machine-caller専用面') makes it less immediately readable than it could be.

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?

The description covers the operational model and return status categories, and an output schema exists to document return values. Still, the combined gaps around required parameter semantics and when to select this tool over sibling tools leave the definition only partially complete for an agent that needs to invoke it correctly without additional context.

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 description coverage is only 40%, so the description needed to compensate for the undocumented required parameters such as session_id and operation_id. The tool description does not explain these or their relationship to the issue/recover actions; only the schema's text and remote descriptions provide any parameter-level meaning.

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 specific actions ('issue/recover') and a specific resource ('durable operations of Claude sessions associated with aiterm'), and clarifies that it returns machine-readable statuses ('pending/unknown/completed'). It implicitly distinguishes itself from observer/pty-facing tools by stating it has no Observer-specific logic, though it does not explicitly name a sibling tool.

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 'machine-caller専用面' gives clear context that this is meant for programmatic callers, and 'Observer固有ロジックは持たない' implies it should not be used for observer behaviors. However, no alternative tools or explicit when/when-not conditions are named, so the usage guidance remains mostly implied.

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