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

Annotations cover the safety profile (non-destructive, idempotent, open-world), but the description adds what the annotations cannot: nothing is connected until the person approves, no password or key is passed through the tool, and the country is immutable after account creation. These are material operational facts an agent must know.

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 tight sentences, each earning its place: action and return, the approval caveat, then the follow-up and the immutability warning. The verb and return are front-loaded.

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?

Given an output schema already exists, the description needn't detail return fields, yet it still characterizes the return (a link to approve) and warns about the irreversible country choice. Nothing needed to invoke it correctly is missing.

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% and the country property already documents "Ask them — never infer it" and the first-time-only behavior, so the description's note about immutability largely repeats structured data. It adds emphasis but not new syntax or meaning beyond the schema.

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?

States a specific verb and resource ("Starts connecting Stripe to a page") and describes the two-step approval flow. It is trivially distinguishable from siblings like connect_google, connect_telegram, and connect_zoom.

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?

Names the follow-up alternative explicitly ("Check list_connectors afterwards") and gives a concrete precondition: confirm the country with the person before calling. It also clarifies that nothing is connected until the user approves, which tells the agent this is a kickoff step, not a completed action.

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