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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral context: the deterministic offer-selection order, the per-banner aggregation, and the null-return semantics for unmatched items. Missing details are minor, such as whether results are ordered or truncated for large item lists.

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 compact sentences, front-loaded with the per-item/per-banner scope and the selection order, then the fallback. The nested parenthetical is dense but each clause carries distinct information; nothing is padding.

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 contract and does so: best offer per banner, per-banner totals, and null for unoffered items. For a 4-parameter read-only tool this is nearly sufficient; only result ordering and behavior on large item lists are left unstated.

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% and each parameter (near, items, banners, radiusKm) is documented with format examples and bounds, so the baseline is 3. The description adds only the phrase 'near a place' and 'each banner', restating schema meaning rather than extending it — no extra constraints such as the 30-item cap or default radius.

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 operation: for each requested item, return the best comparable flyer offer at each banner near a place, plus per-banner totals. The tie-break rule (priced offers first, name match, then lowest unit price) makes the output contract concrete, and the closing clause routes the no-offer case to a named sibling (shelf_prices), so an agent can distinguish it from search_offers and shelf_prices without opening a schema.

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 explicit routing guidance for the failure mode: items with no flyer offer come back null and should be retried with shelf_prices. It does not say when to prefer compare_items over search_offers or price_range for multi-item lookups, so the alternative-selection guidance is partial rather than complete.

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