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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safe read profile is covered. The description adds real value by disclosing the output ref format and the brand-logo coverage caveat for Tabler, though it omits rate limits or result-ordering mechanics.

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 dense sentences, front-loaded with the core action and return shape, then a practical caveat. Every sentence earns its place, though the second sentence's ellipsis shorthand is slightly informal.

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?

No output schema exists, but the description compensates by explaining the return ref format. With annotations covering safety and the schema covering all parameters, an agent has enough to call this correctly; only edge behavior like empty results is unaddressed.

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%, so the schema already documents q, set, kind, and limit. The description reinforces that results span every set and mentions set shorthand (tb/fa/si) but adds no syntax or default details beyond what the schema provides.

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 (Search) and resource (every icon set) and even specifies the return format (`ref-icon:<set>/<Name>` refs for Icon nodes and Button/Link icon.value). This clearly distinguishes it from sibling lookups like find_image, find_video, and search_blocks.

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 context for use and a useful routing hint: Tabler (tb) lacks many brand logos, so brands come from fa / si. It does not explicitly say when NOT to use it versus find_image, but the icon-specific framing is strong.

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