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

Annotations already declare readOnly and non-destructive, so the description isn't burdened with safety disclosure. It still adds real behavioral context: the cardinality limits per view mode, the fact that output includes images, reported delivered prices, card shortlists and app handoffs, and that data remains available without UI — an important trait for an agent that may consume results headlessly.

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?

Two sentences, no filler, with the mode/cardinality rule front-loaded. The second sentence packs several content features into one list, which is dense but still readable and earns its place.

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?

An output schema exists, so return values needn't be enumerated in prose, and annotations cover the safety profile. Combined with the cardinality rules and the headless-data note, the description is complete enough to call correctly; only explicit sibling disambiguation is missing.

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 50%: market and language are documented in the schema, while view and set_ids are not. The description partially compensates by tieing set_ids cardinality to the view mode (1-6 for cards, 2-4 for comparison), which is a constraint the schema's minItems/maxItems do not express. It says nothing about the view enum values themselves or the default, so it only partially fills the gap.

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 names a concrete action and resource: render 1-6 set IDs as shopping cards or 2-4 as a side-by-side comparison. That is specific enough to distinguish it from data-returning siblings like get_set_details or get_set_offers, though it never explicitly contrasts itself with the similarly-named compare_sets sibling.

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?

'After searching or choosing sets, show the final...' gives a sequencing cue that this is a terminal presentation step, which is useful context. However, it offers no exclusions or named alternatives (e.g., when to use compare_sets instead of the comparison view), so the agent must infer the boundary from the sibling names.

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