Reply to a message

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

Annotations only indicate non-readonly, non-idempotent, and non-destructive behavior. The description adds valuable context beyond that: it handles subject prefixes and In-Reply-To/References headersWorld, and it emphasizes that the action sends immediately. This is critical behavioral information for an agent deciding whether to invoke a side-effecting operation.

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?

Three short sentences deliver the essential message efficiently: what the tool does, why it behaves as a reply, and that it sends immediately. Every sentence earns its place, and the immediate-send warning is front-loaded at the end for emphasis without being wordy.

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 5-parameter send action with no output schema, the description covers the key behavioral risks and thread semantics. It does not mention return values, errors, or delivery guarantees, but the schema fully documents parameters and the tool is simple enough that those omissions are minor.

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%, so the schema already documents every parameter clearly. The description adds no parameter-level meaning beyond the schema, such as how body, is_html, or reply_all interact. A baseline score of 3 is appropriate because the schema carries the full semantic weight.

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 opens with a specific verb and resource: 'Send a reply that stays in the original thread.' It clearly distinguishes the tool from sending a new message by emphasizing thread continuity and header handling. It also differentiates from draft creation with the explicit warning 'This SENDS immediately.'

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 implies when to use the tool: when the intent is to reply within an existing thread rather than start a new conversation. It also signals that the tool sends immediately, contrasting with a draft workflow. However, it never explicitly names alternatives like send_message or create_draft, nor states when not to use it.

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