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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile, so the description's job is to add context — and it does extensively. It discloses return semantics: winner/share/price-gap output, the `situation` tag enum (amazon_in_box | reseller_swarm | tied_price | price_gap), revenue-at-risk computed from operator_a's perspective, and the whitespace/expansion-targets concept. No contradiction with annotations (read-only compare aligns perfectly).

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?

Three dense sentences with no filler; the core purpose and output semantics are front-loaded before usage triggers and sort options. It is long relative to typical descriptions, but every clause carries information — there is no repetition of schema contents or restatement of the tool name.

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 10-parameter tool with no output schema, the description carries the return-value burden and does so thoroughly: winner, shares, prices, gap, other-seller counts, Amazon box status, situation tags, revenue-at-risk, and whitespace are all explained. Minor gaps remain — 'sanitized prices' is undefined and the 'high-revenue' whitespace threshold is unspecified — but the optional parameters are fully handled by the schema, so the definition is largely 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 description coverage is 100% across all 10 parameters, so the baseline is 3. The description still adds meaning the schema lacks: it defines 'contested' as ASINs BOTH operators carry, frames whitespace as high-revenue expansion targets, and enumerates the `situation` tag values — all of which inform how contested_only, include_whitespace, whitespace_for, and the result structure should 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 and resource: 'ASIN-level buy-box head-to-head between two operators (sellers).' It enumerates concrete outputs — winner, buy-box share, sanitized prices, price gap, situation tag, revenue-at-risk, and whitespace — making the pairwise-contested scope unmistakable. This clearly differentiates it from single-operator tools (operator_top_asins), single-ASIN tools (asin_buybox_history), and cross-marketplace tools (xmkt_pricing_compare).

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?

Explicitly lists five concrete user-query triggers: 'compare seller A vs seller B', 'where do these two sellers overlap / compete', 'who wins the buy-box between them', 'show me the head-to-head', and 'what does A sell that B doesn't'. However, it never states when NOT to use it or names a specific alternative sibling, stopping just short of full exclusion guidance.

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