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

Annotations already declare this is a non-readonly, non-destructive, non-open-world, non-idempotent write. The description adds real value beyond that: it explains the draft-vs-sent semantic, the one-tap send by the human, the 'via <your app>' labelling, and a privacy restriction on sensitive content. It stops short of describing what is returned or whether a draft can be revised or withdrawn.

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?

The opening sentence front-loads the purpose well, but the rest is a dense run-on mixing an inline Swedish example, a parenthetical of three UI surfaces, quoting instructions and a privacy rule. Every element is relevant, yet the packed sentence structure makes it harder to scan than it needs to be.

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 five-parameter mutation tool with no output schema, the description covers the draft lifecycle and content restrictions but omits what a successful call produces (a draft id?), how the agent should confirm or clean up a draft, and any failure modes such as an unresolvable recipient. Adequate but with clear gaps.

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 80%, so the schema already documents to, text, about, links and replyTo, including the read_chat linkage for replyTo. The description adds only the framing that text is in the person's voice and the example recipient name, both of which are essentially restatements of the schema; 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?

The description states a concrete action: composing a message draft to a friend, group chat or family, with an example utterance. The verb+resource are unambiguous, but it never names sibling alternatives such as message_member, pro_message or reply_in_thread, so sibling differentiation is left to inference.

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?

Usage is implied by 'Write to a friend, a group chat or the family', and the note that the recipient sends it with one tap clarifies the workflow. However, there is no explicit statement of when to choose this over message_member or reply_in_thread, nor any exclusion; the 'say I've made a draft, never sent' line governs agent phrasing rather than tool selection.

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