Search grocery offers

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

With no annotations, the description carries the full burden and does well: it discloses that unit prices are not always comparable across basis units (kr/kg vs kr/stk), that 'computed' confidence means unverified against the flyer, that results sort cheapest-first, and that priced_only defaults to true (hiding unpriced offers). This is meaningful behavioral context beyond the bare schema.

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?

Three sentences, zero filler. Every sentence adds distinct value: what it searches, how it sorts, and the two critical interpretation caveats. Front-loaded with the purpose, caveats appended as the essential reading guidance.

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?

For a 10-parameter no-output-schema search tool, the description covers the key behavioral hazards (unit comparability, confidence status, sorting, pricing filter default). It doesn't enumerate each filter's semantics, but the critical correctness risks are addressed. With no output schema, the description adequately orients the agent on what to expect and how to interpret results.

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%, with several parameters (basis, category, limit, priced_only, max_unit_price, min_discount_pct) lacking descriptions in the schema. The description partially compensates by explaining the basis-unit comparability caveat, but does not individually clarify basis, category enum semantics, or limit behavior. The most behaviorally critical caveat (unit_price_basis pairing) is covered in prose, adding real value.

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 uses a specific verb ('Search') with a clear resource ('this week's Norwegian grocery offers'), and explains matching behavior. It distinguishes itself from siblings by explicitly noting free-text matching on product heading plus filtering, and its cheapest-first sorting.

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?

The description explains the matching/filtering behavior and sorting. It gives clear guidance on interpreting unit_price with unit_price_basis and treating computed confidence as unchecked. It doesn't explicitly state when NOT to use it vs alternatives like cheapest_by_category or compare_ingredient, but the search-orientation is clear.

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