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

The line 'Counts as a use' is genuine side-effect context that explains why annotations mark this non-readOnly and non-idempotent — quota consumption is exactly the behavior an agent needs to know before invoking. It doesn't cover auth requirements, but annotations already carry the safety profile, so this exceeds the bar.

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 with no filler; the workflow hint and the 'counts as a use' caveat both earn their place. Slightly terse given it omits any statement of what the tool returns.

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 two-param render tool with no output schema, the description should clarify what comes back (the rendered text, a preview object, etc.). 'Ready to send' gestures at it but never states the return shape, leaving a small but real gap.

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 coverage is 100%, so both savedReplyId and conversationId are already fully documented in the schema. The description's mention of variable types (first name, your name, product) is contextual flavor rather than parameter guidance, so the baseline 3 applies.

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?

States a specific action on a specific resource: renders a saved reply with its variables filled for one conversation. It distinguishes itself operationally by naming reply_to_conversation as the downstream step, though it doesn't differentiate from near-siblings like draft_reply_with_ai or use_email_template.

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?

Implies the workflow by noting the result is 'ready to send with reply_to_conversation,' which tells the agent this is a pre-send step. However, it gives no explicit when-not guidance and doesn't contrast against alternatives that also produce send-ready content.

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