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

Annotations already declare read-only, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new behavior: which registries are queried, that results aggregate to one row per query, and the per-call cost ($0.005 per product-check) — cost disclosure is real value an agent cannot get from annotations. It omits rate limits and what happens when a source is unreachable.

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 description is front-loaded with the user-facing question, then sources, then audience, then price — a sensible order with little redundancy. A few marketing phrases ("Built for AI agents... and for people who want...") do not earn their place but are brief enough not to obscure the content.

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?

There is no output schema, and the description compensates by stating the return shape: yes/no per query, recall date, hazard, remedy and official link. Combined with the source list and pricing, an agent has enough to call and interpret it; only failure/degradation behavior and result-ordering beyond maxMatches' "newest first" are absent.

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 100%, so the schema already explains euWeeks, queries, sources and maxMatches with examples. The description only restates the accepted identifier formats at a high level, adding nothing about formatting edge cases or how source selection affects results. Baseline 3 is appropriate.

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 opens with the exact question the tool answers ("is this product recalled anywhere, and for what hazard?") and names the accepted identifier types (name, brand, model, UPC/EAN, VIN) plus the four source registries. No sibling tool covers recalls, and the response shape (one row per query) is stated, so an agent can identify the tool at a glance.

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 implied context through audience framing (e-commerce, resale, procurement, compliance) and the phrase "one sourced answer instead of four searches," which hints at consolidation versus separate lookups. However, it never states when NOT to use it or names an alternative (e.g. identifier_resolver for ambiguous barcodes), so routing 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.