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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real value beyond them by disclosing what is returned — including derived fields like price per kg and a comparative summary (cheapest, most expensive, which have sizes or required choices) — which tells the agent the output shape without an output 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?

Two sentences, front-loaded with the verb and scope, then the required input source. The attribute list is dense with parentheticals but every element is informative; only the nested parentheses ('price (and sizes, price per kg)') slightly hurt scannability.

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 burden of describing results, and it does so thoroughly including the summary semantics. Only minor gaps remain: nothing about error behavior when an ID is invalid or belongs to another shop, and the shop parameter's scoping rule is left entirely to the 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 description coverage is only 50%, but the description compensates by restating the 2–5 cardinality (matching minItems/maxItems) and the origin of product_id values. The 'shop' parameter and its 'from find_shops' / own-address exemption are documented in the schema but not reinforced here, leaving a small gap.

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?

Specific verb ('Compare') plus resource ('2–5 specific products side by side') and an explicit enumeration of the compared attributes (price, sizes, price per kg, description, options, age limit, prep time, availability). It is clearly distinguishable from get_product (single product detail) and search_products (discovery) by the string of comparison dimensions and the summary output.

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?

States the use case precisely — comparing 2–5 already-identified products — and tells the agent where the required inputs come from ('Get product_id from search_products or get_menu'), which is the critical routing instruction. It stops short of naming an explicit alternative or exclusion (e.g. 'use get_product for a single item's full detail'), so it is strong but not fully specified.

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