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

Even though annotations already flag destructiveHint=true, the description adds crucial behavior: it sends a reply, reveals metered contacts, and launches a campaign, requires a two-step token approval, and shows the exact error/return shape. No contradiction with annotations.

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 sentences pack a clear operation, effects, guardrails, and error flow with no filler. Key behavior is front-loaded before details.

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 destructive but gated tool, the description explains the authorization loop, metering consequence, guardrails, and where action_id comes from via the schema. No output schema exists, but the error shape and orchestration are disclosed; an agent can invoke it safely.

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 the baseline is 3; the description adds value by defining approval_token as the token from a prior approval_required response and explaining the call sequence. This is more than parameter listing, but not by a huge margin because the schema descriptions are already good.

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 the exact operation — approve a queued autopilot action and execute it — and spells out concrete consequences (draft sent, proposal reveals contacts and launches). This clearly distinguishes approve_autopilot_action from siblings like get_autopilot or reject_autopilot_action.

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 provides clear context for how the approval flow works: call without the token to get an approval_required error plus token and summary, then call again with the token. It does not explicitly name when-not-to-use or alternatives, but the two-step flow and 'same gated paths as dashboard approve' are sufficient for selection.

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