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

Annotations already declare readOnlyHint/destructiveHint false, so the bar is lower, and the description still adds real context: an interactive UI is opened, `purpose` becomes the picker heading and is echoed back, the selection arrives as ids in context plus a merchant message, and a host must support MCP Apps. It does not mention the sibling pick_products_search or what happens on a non-MCP-Apps host, which keeps it from a 5.

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 with the core action, then return shape, then the routing rule — a sensible order with no filler. It is denser than it needs to be in places (the filter enumeration partly duplicates the schema) but every sentence carries information.

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?

For an interactive tool with 8 optional params and an output schema, it covers the essentials: what the merchant does, what comes back, the environment prerequisite, and where the result plugs in. The main gap is behavior on hosts without MCP Apps support and its relationship to pick_products_search.

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 is 3; the description adds meaning beyond the schema by explaining that `purpose` is rendered as the picker's heading and repeated back with the selection, and by framing the filters as in-picker facets. Remaining parameters get no added semantics because the schema already covers them well.

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 — opens a product picker beside the chat — and describes the interaction (search, filter, tick from a picture grid) and the return (product ids plus a merchant message). It explicitly contrasts with search_products, so an agent can route without opening a 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?

Gives an explicit when-to-use condition ("Call it when a selection is theirs to make by looking", a hand-picked page) and an explicit when-not with the alternative named ("products described well enough to search for are search_products"). It also names the downstream consumers, create_catalog and edit_catalog addProducts.

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