Compare one ingredient across chains

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

The description provides critical behavioral disclosure by distinguishing two data fields: `discount_pct` (retailer's own claim) vs `vs_baseline_pct` (the tool's inference). It explicitly warns not to present the second as the retailer's claim. With no annotations provided, the description carries the full burden, and it does this exceptionally well by warning about a subtle data provenance pitfall.

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 compact and front-loaded with the core purpose ('Price one ingredient across every chain this week, with a baseline from earlier weeks'). It then adds essential field-disambiguation context. The warning clause is valuable but slightly wordy; could tighten 'is null for most offers' phrasing, but overall efficient.

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 only 2 parameters, no output schema, and no annotations, the description covers the essential aspects: what the tool does, temporal scope, and the critical dual-field semantics with a correctness warning. It's complete for an agent to correctly select and use the tool for this purpose.

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 50% (only `ingredient` has a description). The description meaningfully adds to parameter understanding by explaining the two computed fields (`discount_pct`, `vs_baseline_pct`) in the output, which relate to how results should be interpreted. However, it doesn't clarify `week` format/behavior beyond what the schema lacks.

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 specific verbs ('Price', 'Compare') plus the resource ('ingredient') and clear scope ('across every chain this week', 'baseline from earlier weeks'). It distinguishes from siblings by emphasizing the cross-chain comparison aspect, though it doesn't explicitly name alternatives.

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 usage context (weekly cross-chain pricing with historical baseline) but doesn't explicitly state when to use it vs price_history (which likely covers the historical angle) or cheapest_by_category (similar comparison but by category). No explicit exclusions or alternatives are named.

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