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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Pure data fetch (no AI analysis).' Beyond that, it discloses two important behaviors the annotations cannot express: calling without `marketplace` fetches nothing and returns "MARKETPLACE NEEDED", and calling without `sections` returns a summary plus a list of which sections hold data. The 'several KB of detail you will rarely need' warning about requesting all six sections is genuinely additive context.

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 long but not padded: core function and contents are front-loaded, followed by purpose differentiation, the sections call-pattern warning, interpretation guidance, and the marketplace rule. Every sentence carries operational value for a tool with two optional parameters and no output schema, though it could be tightened slightly without losing meaning.

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 data-fetch tool with no output schema, the description is complete: it enumerates the response contents in detail, explains the default summary behavior and how to discover available sections, states the marketplace requirement and its failure mode, and notes that money is in the marketplace's local currency. Nothing an agent needs for a correct first call is missing.

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%, so the baseline is 3 — the schema already documents asin, sections, and marketplace well. The description adds practical semantics above that baseline: `sections` should be omitted first and requested only when the summary is insufficient, and `marketplace` must be the user-named code reused across the conversation with the failure mode spelled out. This exceeds what the schema alone conveys.

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 action — fetching buy box, competing offers, and price/rank statistics for a single Amazon ASIN — and enumerates the exact data returned (FBA vs FBM counts, price levels, out-of-stock share, ownership history). It also distinguishes itself from siblings explicitly: 'for demand and revenue estimates use analyzeProduct instead.' An agent can tell this apart from the 12 siblings without inspecting schemas.

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 scopes the tool to reseller/online-arbitrage questions and excludes private-label research with a named alternative. It adds concrete interpretation guidance (buy box held by Amazon or one seller means little room, many FBA offers means price competition, high out-of-stock share means supply gaps) and a precise marketplace protocol: ask once, reuse the code for every later call, never assume the US.

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