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

Annotations only declare it is not read-only and not destructive; the description adds three behavioral facts annotations cannot express: no side effect occurs on the customer side, one plan AI reply is consumed per call, and a Pro+ subscription is required. Those are exactly the traits an agent needs before invoking a metered AI tool.

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, no waste, and the most decision-relevant fact (nothing is sent, use reply_to_ticket) is front-loaded before the cost and plan-tier notes.

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-parameter tool with a small schema and no output schema, the description covers purpose, side effects, follow-up, cost and access tier. It stops short of saying whether the draft text is returned inline in the response, which is the one thing an agent reviewing the result would want confirmed.

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 parameters are already documented with examples. The description adds only the implicit idea that the note is a short input expanded by the AI, which is marginal beyond the schema's 'What the reply must say, in a few words.' 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 transformation ('turn a short note into a full reply to a ticket's customer') on a specific resource. The mention of 'ticket' implicitly separates it from the sibling draft_email_reply, and the language-adaptation detail adds scope the name does not convey.

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?

Explicitly states when this is only a draft ('Nothing is sent: show the draft') and names the follow-up tool and condition ('then send it with reply_to_ticket'). It also gives prerequisites ('Needs Pro or higher'), so the agent knows whether it may call it at all.

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