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

With no annotations, the description carries the full load and does well: it discloses that the reply supersedes any pending draft (a destructive side effect), that it is logged on the ticket, and that it emails a real customer (an irreversible external effect). What is missing is any statement about permissions or auth requirements for sending from the support address, and whether superseding a draft can be undone.

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, with the core action first, then the routing condition, then the side effects and the customer-facing warning. Every clause carries information; there is no filler or repetition of the title.

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 mutation tool with no annotations and no output schema, the description covers the essentials an agent needs before committing: that it sends for real to a customer, that it replaces a pending draft, and that it is recorded on the ticket. The remaining gap is the undocumented conversation_id and the absence of any note on what is returned or required permissions.

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 50%: body is documented as plain-text while conversation_id has no description at all. The description adds useful framing about the reply landing in the same email thread, but it does not explain what a conversation_id is, where to obtain it, or confirm the body is plain-text only. With half the parameters undocumented, a baseline 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 names a specific verb pair (write and send), the resource (a reply on a conversation), and the delivery channel (same email thread, from the product's support address). It also distinguishes itself from the draft-approval siblings by stating 'use when there is no draft, or to write your own', so an agent can separate it from Support_Approve_Draft without opening either schema.

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?

It gives an explicit selection condition: use this when no draft exists or when the agent wants to author its own text. That is clear guidance rather than implied usage. It stops short of naming Support_Approve_Draft by name as the alternative for the draft-exists case, so routing is slightly inferential rather than fully spelled out.

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