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

Annotations already declare this as a read-only, idempotent, non-destructive, non-open-world search, so safety is covered. The description adds genuinely useful behavior beyond that: the filter-relaxation cascade and its exact drop order, that 'kind, caffeine, organic, fairtrade, vegan, iced and both price limits are never dropped', that results are best_match-ordered by default, that out-of-stock items are hidden, and that prices are live and VAT-inclusive. These are real behavioral disclosures, but the description still omits output shape/pagination, leaving it solidly middle rather than exceptional.

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?

Purpose is front-loaded and every clause carries information, but the middle is a dense run-on that packs filter relaxation, units, ordering, stock behavior and sibling routing into consecutive semicolon-linked clauses. It is efficient but slightly heavy to parse in one pass.

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 16-parameter search with an output schema present, the description covers what an agent needs: scope, filter conjunction behavior, unit conventions, defaults, ordering, stock visibility, and the degradation path when nothing matches. Return-value explanation is correctly delegated to the output schema.

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 100%, so the baseline is 3, and the description adds meaning the schema does not: it disambiguates max_price as per pack in pounds versus max_price_per_cup_pence per cup in pence, states the AND-semantics of 'every filter given applies at once', restates the limit range/default, and frames query as the customer's own words that may be dropped. That is meaningful added semantics over an already-documented schema.

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 ('find, browse or choose tea, coffee, hot chocolate or other drinks to buy from teas.co.uk') and names the shop explicitly. It differentiates from siblings by naming get_product, compare_products and add_to_basket and excluding general tea knowledge, so an agent can place it without opening another 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 an explicit when-to-use trigger ('when someone wants to find, browse or choose'), an explicit when-not ('Not for general tea knowledge'), and routes three adjacent needs to their alternatives. Nothing about selection 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.