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

Annotations already establish readOnly and openWorld, so the lower bar applies. The description adds genuinely non-obvious behavior: newest-first ordering, fixed 50-per-page paging via next_cursor, and the rule that French Safety Gate alerts merged into a RappelConso fiche are not duplicated — the last point is exactly the kind of cross-source behavior that isn't inferable from structured fields.

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 dense sentences with no filler: scope, sources, ordering, page size and the cursor come first, then the narrowing options, then the dedup caveat. Every clause carries information an agent would otherwise have to guess.

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 must carry the paging contract, and it does (50 per page, next_cursor, newest first). It also covers the merge/dedup case. What it omits is what a recall record contains and whether results span both sources by default versus requiring source, a minor residual gap.

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 60%, and the schema already documents since (YYYY-MM-DD, 2018-01-01+), cursor as next_cursor, and country as ISO alpha-2 notifying country. The description's 'narrow by source, category or the notifying country' largely restates the schema and adds no syntax, default, or interaction detail, so 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?

States a specific verb and resource (list product recalls), the two data sources (RappelConso, Safety Gate), ordering and page size, and the deduplication rule that separates it from a naive merged list. It is clearly distinguishable from the sibling check_product_recall, which is a targeted lookup rather than a feed.

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 clear operating context: use a since date, narrow by source/category/country, and follow next_cursor for additional pages. It does not explicitly say when to prefer this over check_product_recall or when-not to use it, so it stops short of full routing guidance.

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