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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context beyond annotations: it returns the total in every chain that sells all items, the cheapest chain, the saving versus the most expensive, chains missing items, and the best split between two chains. This gives the agent a clear picture of the output's richness without needing an output schema. It doesn't mention edge cases like empty results or error handling, but the annotations cover the safety aspects.

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?

The description is a single, well-structured sentence that front-loads the core purpose ('Given a shopping list... returns the total in every chain') and then enumerates the specific outputs. Every clause adds value: the input format, the comparison scope, the cheapest chain, the saving, missing items, and the two-chain split. 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?

For a tool with one parameter, no output schema, and rich annotations, the description is quite complete. It tells the agent what input is expected (barcodes and quantities) and what outputs to expect (totals, cheapest, saving, missing items, best split). It doesn't specify the exact format of the return value, but without an output schema, the description's enumeration of outputs is sufficient for an agent to understand the tool's capability. A 4 is fair because it could mention how the 'best split' is calculated or whether the result is sorted, but these are minor gaps.

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 0%, so the description must compensate. The description explains that the 'items' parameter is a shopping list of barcodes and quantities, which directly maps to the schema's structure. It adds meaning by clarifying that the list is used for basket-level comparison, not just individual price lookup. However, it doesn't detail the qty default or constraints, but those are already in the schema. With 0% coverage, the description does a good job of bridging the 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?

The description uses a specific verb ('returns') and clearly identifies the resource ('shopping list') and the operation's scope: comparing totals across chains, identifying the cheapest, the saving versus the most expensive, missing items, and best split between two chains. It distinguishes itself from siblings like get_product_prices and rank_chains by focusing on a basket-level comparison rather than individual product prices or chain ranking.

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 implies when to use this tool: when you have a shopping list of barcodes and quantities and want to compare totals across chains. It doesn't explicitly state when not to use it or name alternatives, but the context signals and sibling names (get_product_prices, rank_chains) make the use case clear. A 4 is appropriate because the context is clear but exclusions are not explicitly stated.

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