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

Annotations declare destructive=true, idempotent=true, readOnly=false; the description adds the concrete effects that annotations can't convey – change types stay off and Autopilot stops prompting – plus a reversibility path via channel_plan_save. This is real added context beyond the structured safety profile, short only of stating what is returned or whether an existing connection is required.

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 tight sentences, with the primary effect front-loaded and the alternative/reversibility note second. No filler, though the phrasing 'its change types stay off and Autopilot stops asking' is dense enough that an agent must infer the subject is the client's channels.

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 two-parameter mutation with no output schema, the description covers the effect, the reversibility path, and the alternative tool. It is missing only whether preconditions exist (e.g., an already-connected account) and the response shape, both minor given the annotations.

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 50%: 'client' is documented as coming from list_clients, while the 7-value 'channel' enum has no per-value description. The description only loosely maps to them via 'for this client' and 'newly connected account', adding mild meaning about which channel is affected but no format or selection guidance for the enum.

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 specific action (declining to let Autopilot work a newly connected account for a client) and its consequence, which distinguishes it from channel_plan_save and channel_plan_approve. It never uses the verb 'decline' explicitly, relying on the tool name to convey that, but the intent is still inferable.

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 gives the selecting condition (the agency doesn't want Autopilot on a newly connected account) and names the alternative route: 'A plan can still be made later with channel_plan_save if the agency changes its mind.' Clear when-to-use and a named sibling, though no explicit statement of when-not to use relative to channel_plan_approve.

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