aura_award_search

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

With no annotations, the description carries the full burden. It usefully discloses the local-index-first / single live-refresh-on-empty caching behavior, but says nothing about permission needs, rate limits, latency, or what distinguishes a live call from a cached one.

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?

Purpose is front-loaded, the mode list is compact, and the caching note closes efficiently. The mode enumeration is a dense run-on, but little is wasted.

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?

For a 15-parameter, 0%-coverage tool with no output schema and no annotations, the description leaves most filters and their interactions undocumented. Mode is covered, but an agent cannot reliably invoke the filter parameters.

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 0% across 15 parameters, yet the description only addresses mode (whose enum values the schema already lists). Filters like award, color, tags, studio, library, category, technology, scrollModel, easing, limit, and offset are left entirely unexplained, so the description does not compensate for the coverage gap.

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 ("Search award-winning website references (Awwwards)") and enumerates four modes with what each returns, which is rare specificity. It does not name its closest siblings (aura_award_inspect, aura_award_index) to disambiguate, so it stops short of 5.

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 mode breakdown gives clear selection context — an agent can tell which mode yields ranked site refs vs taxonomy vs element examples vs motion studies — plus the "local index first, one polite live refresh when empty" operational note. There are no explicit exclusions pointing to aura_award_inspect or aura_award_index for non-search operations.

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