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

Annotations already declare readOnly/idempotent/no-open-world, and the description adds genuinely new context: the purchase happens in the human's browser, not in the tool ("This call never buys anything"), and the api_key affects visit attribution. Missing only things like link expiry or single-use behavior.

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 short sentences in priority order: trigger, what you get, what does not happen, plus the attribution tip. No filler or restatement of the title.

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?

Covers trigger, return value, and the critical non-mutation guarantee with no output schema needed. Minor gaps (link lifetime, reuse, whether the agent must surface the URL to the human) are the only thing keeping it from full marks.

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 100% schema coverage the baseline is 3, but the description adds meaning to api_key that the schema only hints at — passing it makes the visit count for the agent. That is a real semantic addition beyond the structured field.

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 concrete outcome: it returns "the one page where they buy it," and names the sibling (find_offers) that produces the offer_id it consumes. An agent can tell this apart from find_offers/list_offer without opening the schema.

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?

"Use when your human picked an offer from find_offers" gives an explicit trigger and prerequisite. It does not spell out when-not or name an alternative path, but the prerequisite chain makes the ordering unambiguous.

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