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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the description isn't required to explain safety. It adds genuinely new behavioral context beyond the annotations: the operation requires the user's MyGroceryPal account, and it distinguishes the primary result (cheapest single store) from the secondary heuristic (split across two or three stores only when cheaper or covers more of the list).

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?

A single front-loaded sentence that delivers the computation, the output shape, the conditional logic for split suggestions, and the auth requirement with no wasted words.

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?

An output schema exists, so return-value structure needn't be described; the description covers the computation performed, the decision rule for split suggestions, the item limit, and the account prerequisite. For a single-parameter read-only tool this is enough for an agent to call it correctly.

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 effectively 0% at the top level (only productId carries an inline description pointing at search_grocery_prices). The description compensates partly by restating the basket size ceiling of 30 and framing items as products in a basket, but it says nothing about quantity semantics, duplicate productIds, or what happens with unavailable products.

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 ('Total a basket ... at each UK supermarket') and enumerates the three concrete outputs: cheapest single store, split suggestion, and conditions for suggesting the split. The 30-product cap is stated, so an agent can tell exactly what this tool computes.

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?

Usage is implied by the description (multi-product basket comparison versus the sibling search_grocery_prices, which the schema references for productId lookup), and the account prerequisite is stated. However, it never explicitly says when to prefer this over check_price_history or that a single-item lookup should use search_grocery_prices instead.

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