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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, idempotentHint=false. The description adds valuable context beyond annotations: the gating rule (autonomous agent CANNOT declare, only human or graduated operator), the sensitive-tier approval flow, and the behavioral consequence (agents stop asking to connect Stripe). It doesn't fully detail what 'destructive' means here (e.g., overwriting existing channels), but the gating and approval context substantially enrich the annotation profile.

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 description is dense but every sentence earns its place: purpose, gating, downstream effect, preconditions, and approval flow. It is front-loaded with the core purpose before the gating details. Slightly long, but the complexity of the gating/approval rules justifies the length.

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 sensitive, gated mutation tool with no output schema, the description covers the critical context: who can call, when to call, what happens after, and the approval nuance. The only minor gap is not describing the return value, but for a state-setting tool that is not essential. The description is complete enough for an agent to invoke correctly.

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 schema already documents all three parameters. The description adds meaning beyond the schema by explaining the semantic significance of 'none_yet' (pre-revenue, exclusive) and the real-world consequence of the channels value (routing to the right revenue tool). The schema itself also has a strong description for 'none_yet' exclusivity, so the description's added value is moderate but real.

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 verb ('Declare where this business makes money') and enumerates the exact channel values, making the tool's purpose unmistakable. It also distinguishes itself from sibling tools by explaining the downstream routing effect (agents stop asking to connect Stripe, routed to the right revenue tool), which separates it from generic setup tools.

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?

The description gives explicit when-to-call guidance: call get_setup_state first, only call again if 'Revenue channels' already shows done and the operator says it changed. It also states who can call it (human/chat or graduated MCP operator, company managers) and when not to re-ask in chat. This is unusually complete usage guidance.

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