Hey365 refine draft

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

No annotations are provided, so the description carries the full disclosure burden. It states the core mutation (modifying an existing draft) but does not disclose what the tool returns, whether the refinement persists, or whether the original draft is replaced. For a mutating refinement tool 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?

A single front-loaded sentence states verb, resource, and mode, with parenthetical examples that clarify the instruction format. Every element earns its place and there is zero 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 2-parameter tool with full schema coverage, the description is nearly sufficient. However, with no output schema and no annotations, it fails to state what the agent should expect back (the refined draft text) or that a draft must already exist in the session. The workflow relationship to sibling tools is only implied.

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 100% — both itemId and instruction have clear Japanese descriptions, so the baseline of 3 applies. The tool description adds only marginal value by framing instruction as natural-language editing examples, partially overlapping with the schema's own examples. No parameter is left undocumented.

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 states a specific verb (修正する/modify), a specific resource (既に提示した返信案, the already-presented reply draft), and the method (natural language instructions), with concrete examples (柔らかく/英語に/短く). The 'already presented' qualifier implicitly differentiates it from sibling draft-creation tools like hey365. The purpose is unambiguous.

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 '既に提示した返信案' implies the tool is only for refining a draft that already exists in the conversation, which is useful context. However, it names no alternatives (e.g., hey365 to create a draft, hey365_send to send) and gives no explicit when-not-to-use guidance. Usage is implied rather than stated.

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