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

ReadOnlyHint already covers safety, and the description adds meaningful non-obvious behavior: it produces a decision packet with do_not_say/safe_phrasing, requires manual approval, includes an artifact audit trail, and never sends. These traits go beyond a generic read-only flag and do not contradict the annotation.

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?

Two sentences with no filler: the first sentence front-loads the primary purpose and key packet components, and the second states the crucial 'never sends' behavior. Every word earns its place.

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 14-parameter tool with nested objects, no schema descriptions, and no usage routing, the description is too thin. It explains the output concept well but leaves the required channel and major optional parameters unexplained; the presence of an output schema lowers the return-format burden, not the input-semantics burden.

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 0% for 14 parameters, and the description does not explain the meaning of any input field. The phrase 'channel constraints' hints at channel/constraints but not enough to guide an agent on required channel, crm_context, inbound_message, persist_artifact, or idempotency_key.

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 action ('Compose') and a specific resource ('relationship-safe correspondence decision packet'), and enumerates what the packet contains (do_not_say, safe_phrasing, channel constraints, manual approval, artifact audit trail). It is clear, but it does not explicitly differentiate from the many other compose/draft tools in the sibling list.

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 never sends the message' gives a useful boundary that this is a drafting/decision-stage tool, so usage is somewhat implied. However, the description gives no explicit when-to-use guidance and does not point to alternatives such as talent_scout_draft_outreach or a send tool.

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