draft_reply

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

With no annotations, the description carries full responsibility for behavioral disclosure. It states the tool uses a local AI model, returns plain text, and crucially does not send. This covers the key side-effect concern. It does not mention potential failures or model-specific nuances, but the core non-sending behavior is transparent.

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 two sentences, front-loads the action and resource, and includes the key constraint (does not send) and pointer (ready to pass to reply_email). Every sentence earns its place without redundancy.

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 no output schema, the description gives the essential return type (plain text body) and explains the intended next step. It could slightly expand on what 'draft' implies (e.g., no persistence), but the core information needed to invoke and use the tool correctly is present.

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%, with clear descriptions for both message_ref and goal. The tool description itself adds no extra parameter-level meaning beyond 'ready to pass to reply_email,' so the baseline of 3 is appropriate.

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 clearly states the action ('Draft a reply to an email'), specifies the mechanism ('configured local AI model'), and explicitly distinguishes itself from the sending operation by noting 'Does not send — use reply_email to review and send.' This disambiguates it from sibling tools like reply_email and compose_email.

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 description provides direct workflow guidance: the output is 'ready to pass to reply_email' and explicitly says not to use this tool for sending, directing users to reply_email instead. This gives a clear when-to-use and when-not-to-use with an explicit alternative.

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