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

Annotations already declare readOnly/destructive/openWorld behavior, so the bar is lower, and the description adds genuinely non-structured facts: caching guidance and 'does not count toward usage limits.' That quota/cost disclosure is the kind of context annotations cannot express.

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 sentences: the first defines the output, the second defines when to call it and how to cache. No filler, and the purpose is front-loaded.

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 parameters and no output schema, the description carries the return-value burden and mostly discharges it by naming the fields returned. It could go slightly further (e.g., whether results are paginated or how many sets are returned) but is adequate to call correctly.

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?

Zero parameters, so baseline is 4. The description additionally describes the shape of the return payload, which is the only semantics available for a no-input tool.

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 ('Lists hosted icon sets by category') and enumerates the returned fields (prefix, name, icon count), which lets an agent distinguish it from search_icons/get_icon by subject matter. It does not explicitly name a sibling or state the contrast, keeping it below a 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?

Gives clear triggering context ('when the user asks about available icon collections') plus an operational instruction to reuse the returned list once per conversation. It lacks explicit when-not-to-use or named alternatives, so it is a strong 4 rather than a 5.

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