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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is settled. The description adds real operational context on top: public and no sign-in, lexical (not semantic) matching, what errors do (isError set), rate-limit retry advice, the suitability/purchase-availability caveat, and the pagination edge case.

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?

Front-loaded purpose, then access, returns, example, edge cases, alternatives, and caveat — all useful and mostly non-redundant. It is dense and slightly long, but every sentence carries information the agent needs, so the size is justified.

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 an output schema present the description needn't detail return shape, and it still briefly flags the returned fields. Combined with pagination, error, and rate-limit guidance for an 8-param optional-filter search, there is nothing material missing for correct invocation.

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 100%, so the baseline would be 3, but the description adds meaning the schema lacks: a concrete example call ({search, limit}), the behavior of an empty search (browses recent software), and the hasMore/nextCursor relationship. It stops short of explaining filter interactions (e.g., combining mode/type/domains), which keeps it from a 5.

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 opens with a specific verb+resource+scope: 'Find live software by keyword before building from scratch,' and then names two sibling tools by their distinct roles (shortlist vs. cards). An agent can distinguish this from z2h_compare_marketplace_listings and z2h_show_marketplace without opening any schema.

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 states when to use this tool (keyword search before building), names the alternatives explicitly ('Use z2h_compare_marketplace_listings for a shortlist or z2h_show_marketplace for cards'), and even routes empty-search intent to browsing recent software. The hasMore-without-nextCursor guidance tells the agent how to react instead of endlessly paginating.

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