recommend_icons

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

With no annotations, the description carries the full behavioral burden, and it says only that results are 'curated icon suggestions with usage examples.' It does not state determinism, what happens for an unsupported use case, result ordering, or whether limit truncates silently.

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 in the first sentence and the return value follows. The 20-item use-case list is long but functional rather than filler, since it defines the accepted input domain.

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 does mention what comes back (curated suggestions plus usage examples), which is the key gap to cover. A recommendation-only read tool with a fully documented 3-param schema needs little more.

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 limit, style, and useCase are already documented in the schema. The description adds the valid use-case vocabulary beyond the schema's short example list, which is useful but marginal; baseline 3 applies when the schema does the heavy lifting.

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+resource ('Get AI-friendly icon recommendations') and scopes it to UI use cases, which separates it from raw lookups like get_icon or search_icons. However, it never names or contrasts those siblings explicitly, so the agent must infer the boundary between 'recommend' and 'search'.

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 enumeration of supported use cases implies when the tool is applicable, giving an implicit usage signal. It offers no explicit when-to-use vs when-not guidance and does not point to search_icons/get_icon as alternatives for other needs.

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