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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive), so the burden is lower. The description still adds useful behavior beyond that: the dual UCP vs flat calling convention and the paginated return with cursor/has_next_page/total_count, giving the agent a sense of result shape.

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?

Three tight sentences: purpose and scope first, then the UCP calling convention, then the return shape. Nothing is padded and the most decision-relevant information 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?

Covers the bulk of the query surface and, since an output schema exists, it need not describe returns (though it does anyway). The remaining gap is input-side pagination and limit semantics, which the agent would need for multi-page retrieval.

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 0% across 9 parameters, so the description must carry the load. It does name free text, merchant scope, brand, category, in_stock, catalog and meta, but says nothing about `limit` or the input `cursor` used for paging, leaving two parameters unexplained anywhere.

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 ('Search products across all merchants (or one merchant) by free text') and enumerates the filter surface (brand, category, in-stock), so the agent knows this is the broad catalog search. It does not explicitly name siblings like quick_search or lookup_catalog, so the boundary between them must be inferred.

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?

Implies the usage context (cross-merchant or single-merchant free-text browsing) and adds a real calling-convention note for UCP callers passing `catalog`/`meta`. However, it never says when to prefer it over quick_search or lookup_catalog, so alternative selection is left to inference.

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