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

With no annotations, the description carries the full behavioral load and does so well: delivery is deferred pending a human click, the result must be reported as pending not sent, the return status includes email_undeliverable and status_key, and the reply routing. These are exactly the non-obvious traits an agent needs.

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?

Front-loaded with the action, then the critical warning, then escalation and follow-up, in a tight block of sentences. No filler; each sentence conveys an operational constraint.

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?

Complete for a 3-param, no-output-schema mutation tool: it describes the full lifecycle (send → email confirmation → human click → status check), failure handling, and the status_key handoff. Nothing an agent needs to call it correctly is missing.

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 baseline is 3; the description adds meaning by tying reply_to_email to both the confirmation link and the poster's reply, and tying the status_key result to check_message_status. It doesn't add much on post_id/message beyond the schema, so 4 rather than 5.

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 verb and resource (send a message to the poster of an active SUpost listing), and the title plus the sibling check_message_status make the send-vs-check split clear. An agent can distinguish it from search_listings/get_listing without opening the 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?

Explicitly describes the two-phase confirmation flow, when to surface the pending state, how to handle the email_undeliverable result (ask for a different address, don't retry), and points to check_message_status as the follow-up. This is close to explicit when/when-not guidance.

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