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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds genuinely new context: idempotency ('nothing is spent or consumed') and the full enumeration of possible outcomes with their handling. This goes beyond repeating the safety flags, though it doesn't cover rate limits or response format detail.

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?

Front-loaded with the governing question, then the required argument, then the outcome enumeration in a single compact flow. Every sentence carries actionable information with no filler.

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?

There is no output schema, so the description bears the burden of return values and it does so well by listing pending/connected/expired/not_found with handling hints. The only gap is that the poll_after_seconds value referenced for pending is not explained as coming from 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?

With one parameter at 100% schema coverage the baseline is 3; the description adds real meaning by clarifying that the poll_token is the one received with the link, matching the schema's note that it comes from start_connection.

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 verb and resource: it asks whether the founder finished connecting a growth data source and polls for that state. It clearly distinguishes from siblings like start_connection, list_connections, and disconnect_connection by framing itself as the status check for a link already handed out.

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 clear context for use (after handing over a link, pass the poll_token) and per-outcome next steps for pending, expired, and connected. It doesn't explicitly name the alternative tools (start_connection to mint a fresh link), leaving that to inference, so it falls short of a 5.

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