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

Annotations already declare readOnlyHint/destructiveHint=false, and the description clarifies the apparent tension by stating outright "Reads the catalog and changes nothing" while disclosing that panel-side merchant actions happen outside the call and shift page indexes afterwards (recoverable via get_catalog). It also documents the host-dependent rendering, the panel controls, and the text-result fallback for hosts without a panel — well beyond what annotations provide.

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 opener ("One page, or a few, as pictures") is the vaguest sentence and comes before the load-bearing routing and indexing rules, so front-loading is weak. The zero-based convention is effectively stated twice, and the panel-mechanics paragraph is dense prose for a two-parameter read tool.

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, return values needn't be described, yet the definition still notes the text result lists pages plus the editor link. Combined with the panel behavior, index-shift consequence, and sibling routing, an agent has everything needed to call it and anticipate the result.

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%, and the description's zero-based explanation ("the merchant's 'page 1' is index 0") largely restates the schema's own description of `pages`. It adds the conversational mapping from merchant phrasing to index, but says nothing about catalogId beyond what the schema states, and omits the 1–50 item bounds.

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 definition states a concrete verb and resource — render selected catalog pages as pictures, optionally in an MCP Apps side panel — and explicitly routes whole-catalog viewing to preview_catalog. It does not distinguish itself from the sibling preview_page_image, which plausibly overlaps, so the scope boundary is not fully closed.

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 gives the exact selection condition ("For a specific page ('show me page 2', 'let me see the cover')") and names the alternative for the opposite case ("The catalog as a whole is preview_catalog"). It further explains the merchant-facing index convention and the downstream edit path (Point & edit → ids edit_catalog takes), leaving no routing decision to inference.

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