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

Annotations say readOnlyHint=false and destructiveHint=false but cannot convey that nothing is transmitted — the description closes that gap ('Returns the draft only and sends nothing') and warns that the downstream message_send 'cannot be recalled'. It also discloses the prerequisite that an AI provider must be connected under Settings - Integrations, which no structured field carries.

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 critical constraint (draft only, nothing sent) and the send-approval warning are front-loaded before the sibling routing, which is the right order. It runs long at six sentences and 'This is a one-off draft from a prompt' mildly restates the opening, costing a bit of tightness.

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 three-required-parameter tool with no output schema, the description covers the return value ('the draft only'), the side-effect boundary, the auth prerequisite, and the escape hatch to sending. Nothing an agent needs in order to call this 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% with per-parameter descriptions and an enum for provider, so the structured data already does the work. The description adds only a light gloss ('given a prompt', connected provider) and no format or constraint detail beyond 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?

States a specific verb+resource ('draft a reply for a thread') and immediately bounds the outcome ('returns the draft only and sends nothing'), which distinguishes it from message_send without opening either schema. It also explicitly separates itself from the autonomous-agent siblings (agent_upsert/campaign_update, agent_query).

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?

Gives explicit routing: use this for a one-off prompt-driven draft; use agent_upsert plus campaign_update for a self-replying agent; use agent_query to preview how such an agent would answer. It also states the human-in-the-loop condition for escalating to message_send — 'only on an explicit yes for that exact text'.

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