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

Annotations declare readOnlyHint=false and destructiveHint=true, so the description's job is to add operational context, and it does: it discloses the human-in-the-loop review step and the precondition gate on send_now. It does not explain what state the draft creates or why a non-sending operation carries destructiveHint=true, leaving a mild tension an agent may notice.

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, front-loaded with the core action and its exclusion. The telegraphic style ("send_now works only when...") is efficient, though the workflow sentence could be reordered so the review step precedes the send_now caveat.

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 4-parameter, zero-coverage schema with no output schema, the description leaves the recipient parameters and the return value unaddressed, and does not reconcile the destructiveHint annotation with a drafting-only operation. The workflow guidance is solid, but an agent could still mis-target the recipient.

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 description coverage is 0%, so the description must carry the burden, but it only explains send_now's preconditions. The message, phone, and customer_id parameters are entirely undocumented, including whether phone and customer_id are alternatives for identifying the recipient or can be combined — a genuine ambiguity for the agent.

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?

"Draft a text to a customer. Does NOT send." states a specific verb and resource plus the defining negative constraint, and explicitly distinguishes itself from send_text. An agent can tell instantly that this is the compose step, not the delivery step.

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 prescribes the workflow: show the draft to the owner, then call send_text, and gives the condition under which send_now is permitted (owner allowed it and the customer agreed). That is explicit when-to-use guidance with a named alternative. It does not say when to skip drafting entirely (e.g., a purely internal note), so a small gap remains.

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