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

Consistent with readOnlyHint=true, the description frames this as a pure read and adds nuance beyond the annotation: prices are 'current' (point-in-time), the profitability check is explicitly 'coarse,' and the matched-pair output structure with carry-along fields (brand, title, catalog price/range, fulfillment) is disclosed. No contradiction with annotations.

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?

Four sentences with no filler. The opening clause is a near-tautology of the tool name, but the parenthetical '(Amazon vs Walmart)' plus the remaining sentences each carry distinct value: output shape, pair attributes, and usage. Appropriately compact for a 15-parameter tool with the key information front-loaded.

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 return-value burden and handles it well — it specifies every returned field and the data source. The main gaps are advanced filter dimensions (price ranges, match confidence, title contains) and pagination/limit behavior, which are minor relative to the well-covered core flow of matched-pair pricing comparison.

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?

With schema description coverage at only 27%, the description compensates for the two primary filters — 'Single-ASIN or by-brand' maps to the undocumented asin and brand parameters — and its output terms (delta %, profitability, fulfillment) lend meaning to the corresponding filter parameters. However, several filter families (Amazon/Walmart price ranges, match confidence, product_title_contains) remain unexplained in both schema and description, a clear gap at this coverage level.

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 names a specific verb and resource — 'Cross-marketplace (Amazon vs Walmart) pricing comparison' returning matched pairs from mv_product_identity — and enumerates the exact output fields (current Amazon/Walmart price, delta %, FBA profitability check, brand, title, catalog price, fulfillment). This specificity distinguishes it from siblings like asin_comparables or brand_xmarket, which address different comparison angles.

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?

It gives explicit usage context: 'Use for arbitrage / sourcing questions ("cheaper on Walmart?")' along with the two input modes, 'Single-ASIN or by-brand.' It stops short of naming alternatives or exclusion conditions versus related siblings such as asin_profit_calc or find_sourcing_opportunities, so it is a clear-context-but-no-exclusions case rather than a full when/when-not statement.

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