new_winners

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

Annotations already declare readOnlyHint, openWorldHint, destructiveHint=false, and the key idempotentHint=false. The description earns credit by explaining that non-idempotence: the first call seeds the baseline and returns no delta, and later calls return only new entrants. That stateful, call-order-dependent behavior is exactly what an agent needs and is not derivable from the annotations alone.

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 compact sentences, front-loaded with the core action and delta semantics before the polling cadence and sibling pairing. Every sentence carries information, though the two polling-related clauses overlap slightly in intent.

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?

With no output schema, the description must convey the return shape, and it does so adequately by defining the result as new-entrant cards since the last call, including the baseline-seeding edge case. It omits error/rate-limit behavior, which is a minor gap for a polling tool.

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 description coverage is 100% and the single 'award' enum is fully documented in the schema, so the baseline is 3. The description never mentions the award parameter or how it affects the delta, adding nothing beyond the structured 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?

The description states a specific verb ('Poll'), a precise resource ('today's new Awwwards winners'), and the exact mechanism ('as a delta against the previous poll'). It is immediately distinguishable from the read-oriented siblings like search_sites or get_site_details, and it explicitly names its closest relative, watch_site.

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 usage context ('Poll daily for a winners feed') and routes the agent to the sibling tool for a related mode ('pairs with watch_site for structured monitoring'). It stops short of stating an explicit when-not condition or full alternatives, so it is strong but not exhaustive.

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