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

With annotations only covering safety hints, the description carries strong additional weight: it discloses the guarded approval flow (returns {error:'approval_required', approval_token, summary} and requires a re-call with the token), that 'auto' can email real signups, and that dashboard guardrails still apply. This is exactly the behavioral context an agent needs before invoking a mutating tool.

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?

It is a single dense paragraph that front-loads the mode definitions before the guard mechanics. Every clause earns its place; the run-on structure and repeated 'Guarded:' prefix slightly reduce readability.

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 no-output-schema tool, it covers the mode semantics, the deferred-approval token loop, side effects (emails), and the guardrail guarantee — everything an agent needs to call it correctly and handle the response.

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 67%, with connection_id and approval_token described in-schema and only the mode enum undocumented. The description compensates by fully explaining each enum value's meaning, adding genuine value over the bare enum list.

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 opens with a specific resource ('How a program connection handles new affiliate signups') and enumerates the three modes it controls, so an agent knows exactly what is being configured. It does not explicitly name a sibling (e.g. set_autopilot_mode) to differentiate, so it stops short of a 5.

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 clearly explains the semantics of each mode value — 'approve (ask first)', 'auto (each sync approves pending signups your outreach recruited; others still wait)', and 'off' — giving real guidance on which mode to select. It stops short of 5 because it offers no explicit when-not conditions or named alternative tools.

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