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 low. The description adds genuine behavior beyond that: automatic normalization of g→kg and mL/cL→L, which tells the agent it need not pre-convert units before calling.

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 with no filler; the core purpose and normalization rule are front-loaded, and the sibling reference is relegated to the end. Nothing needs trimming.

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 explaining the return shape is optional (and done here, harmlessly). With 100% schema coverage and full annotations, the definition is nearly self-sufficient; only the lack of differentiation from calculate_unit_price keeps it short of complete.

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% and the nested item schema already documents name/price/quantity/unit, so the baseline is 3. The description adds value beyond the schema by specifying which conversions are performed (g→kg, mL/cL→L), clarifying how the 'unit' field will be interpreted.

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+resource ('Compare unit prices of grocery items') plus the normalization behavior, so the agent knows exactly what is computed. It does not, however, differentiate itself from the near-identical sibling calculate_unit_price, which is the main ambiguity in a catalog this size.

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 only implied by the phrase 'grocery items' (multiple items, per the minItems:2 constraint). The only explicit routing is 'See list_bundles for related vie-quotidienne calculators,' which points at a discovery tool rather than naming when to pick this over calculate_unit_price. No when-not conditions are given.

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