send_reply

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

With no annotations provided, the description has the full burden of behavioral disclosure. It only says 'send' and mentions the draft requirement, but does not disclose potential side effects, return values, or whether the action is idempotent or destructive. This is a significant gap for a mutating 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?

The description is concise and front-loaded: two short sentences that state the primary purpose and the required prerequisite. Every word earns its place, and the format is easy to parse.

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?

Given the simplicity of the tool (one parameter, no output schema), the description is still incomplete. It does not explain what constitutes a 'reply' in this system, what happens after sending (e.g., ticket status changes), or any expected return value. The contradiction between the description and schema regarding valid draft sources further undermines completeness.

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?

While the schema covers the parameter at 100%, the tool description adds a misleading restriction by saying the draft_id must come from draft_reply. The schema itself states 'Draft ID from draft_reply or draft_note,' which directly contradicts the description. This reduces the helpfulness of the description and could mislead the agent into rejecting valid draft_note IDs.

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 'Send a previously drafted reply' clearly states the action (send) and target resource (a drafted reply), distinguishing it from sibling tools like send_note by the specific term 'reply' and the reference to draft_reply. It also states the required dependency on a draft_id, which is explicit and useful.

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 usage by stating 'Requires a draft_id from draft_reply,' indicating this tool is used after the drafting step. However, it does not explicitly contrast with send_note or other alternatives, nor does it mention when not to use the tool. Usage is implied but not fully clarified.

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