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

Annotations already declare readOnly/idempotent/non-destructive, so the description is free to add value — and it does, disclosing that marketplace offers carry labels (is_marketplace, marketplace, ships_from, delivery_days_max, shipping_cost, seller_type, store_rating). It does not say what non-marketplace entries look like or how missing/unknown ids are handled, leaving a genuine behavioral gap.

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, core capability front-loaded, and the dense field list is the only place with real informational payload. The trailing user-facing instruction ('mention ships_from and delivery time') is arguably tool-adjacent but earns its place by shaping output use.

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 no output schema, the description carries the return-shape burden and partially meets it by naming the marketplace fields. It still omits the non-marketplace shape, error behavior for invalid or duplicate ids, and whether comparison is limited to same currency/market.

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 description coverage is 50%: market is documented inline (only 'us' supported) but ids is not. The description adds the meaning of ids ('deals by id') and restates the 4-item ceiling, which the schema already enforces via maxItems. Baseline 3 is appropriate given partial coverage.

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 ('side-by-side comparison of up to 4 deals by id') plus a hard cardinality limit, which separates it from the single-deal get_deal and the open-ended search_deals. It never names a sibling explicitly, so the differentiation is inferred rather than stated.

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?

Usage is implied by the phrase 'side-by-side comparison' — you use it when you already have 2–4 known deal ids and want them together. No when-not-to-use condition or alternative tool (get_deal, search_deals) is named, and the second sentence is a presentation directive rather than selection guidance.

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