watch_site

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds non-obvious behavioral context beyond them: the mutation actions (add/list/remove) and the dependency that deltas only surface after new_winners or search_sites refreshes the underlying listing.

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?

Two tightly packed sentences front-load the resource and the three target kinds before the action list and refresh dependency. Every clause earns its place 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?

With no output schema and five parameters, the description adequately covers the targets, the three actions, and how deltas are produced. It leaves some ambiguity about exactly what 'list' returns and how the award filter interacts, though the schema covers those fields.

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 80%, so the schema already documents kind, note, award and pattern. The description reinforces the kind semantics with concrete examples ('ToyFight', 'webgl', URL-slug), adding modest value, but introduces no syntax or format detail the schema lacks. Baseline 3 is appropriate.

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 — a longitudinal watchlist over Awwwards listings — and enumerates the three watchable targets (studio, tag, url) with concrete examples. It is clearly distinguishable from sibling tools like search_sites or new_winners without opening any 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?

The description gives clear workflow context: watches are managed via add/list/remove, and 'the delta is reported by watch_site list after new_winners or search_sites refreshes the listing,' explicitly naming the sibling calls that feed it. It stops short of stating when NOT to use the tool, so it lands at 4 rather than 5.

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