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

With annotations declaring readOnlyHint=true and idempotentHint=true, the behavior is already clear as a safe read operation. The description adds the specific behavioral detail of matching on name, tagline, or category with case-insensitive substring, and limits to live/published tools, which goes beyond the annotation. It does not mention pagination or result ordering, but the output schema likely covers the structure, so minor gap only.

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?

The description is four sentences, each providing essential information: what it searches, what it matches, when to use it, and a result limit. There is no redundancy or filler, and the information is front-loaded with the main purpose in the first sentence. It earns the full score for its efficiency and clarity.

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?

The tool is simple (one parameter) with strong annotations and a full param schema, so the description doesn't need extensive detail. The output limit (up to 20 results) and matching criteria are covered. The only omission is an explicit note about ordering or sorting, but since an output schema exists and the search semantics are clear, it is nearly complete. A score of 4 is justified.

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?

The single 'query' parameter is already fully described in the schema ('Free-text search term, e.g. a tool name, use-case, or category.') with 100% coverage. The description reinforces this by giving examples and specifying the matching behavior (case-insensitive substring), but does not add additional format requirements. Given the schema handles the parameter fully, a slight bonus is given for the clear guidance in the description, but it stays near baseline per the rubric.

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 clearly states the tool searches a catalog of live AI tools by free-text query, matching name, tagline, or category. It explicitly mentions case-insensitive substring matching and scope (live, published tools), distinguishing it from siblings like get_tool which likely fetches a specific tool.

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 explicitly instructs to call this tool first when a user wants to find, discover, or compare AI tools by keyword, use-case, or category, with examples. It implies this is the primary search entry point, contrasting with siblings such as get_tool, list_alternatives, or list_offers, which serve more specific post-discovery purposes.

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