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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), yet the description goes well beyond them: head-terms/page-1 coverage limits, weekly dated samples rather than live data, the free `asin_not_found` outcome, per-25-keyword credit pricing, the +0.5 history surcharge, paid-plan gating, and the derived daily cap. This is exactly the operational context an agent needs before calling a paid, sampled data tool.

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?

Front-loads the core purpose and then layers comparison, history, coverage caveats and cost in a single dense paragraph where each clause carries information. No sentence is wasted, but the density of parenthetical asides makes it slightly harder to scan than an ideally structured definition.

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 an 8-parameter, paid, sampled data tool with no output schema, the description still covers the return shape (per-keyword rows with badge/date and comparison columns), coverage limits, edge cases (asin_not_found) and cost. Nothing an agent needs to call it correctly 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 already 100%, so the baseline would be 3, but the description adds real semantic meaning: passing `asins` turns the call into a competitor comparison that adds organic rank, asins_on_page and gap per row, `gaps=true` filters to that gap set, `history=true` returns the first product's rank across observations, and `limit` is tied to credit burn. This is considerably more than the schema restates.

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?

Opens with a specific verb+resource ("REVERSE ASIN on Amazon US") and precisely defines the returned set: observed keywords whose latest page 1 shows the product, organic or sponsored, with rank, result count, badge and date. The scope statements ("head search terms and page 1 only", "NOT volume figures") separate it from a volume-oriented `keywords` tool and from a rank-tracking `keyword_rankings` tool.

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?

Gives an explicit USE WHEN clause covering three scenarios (which keywords a product ranks for, where competitors appear and the product does not, and rank movement over time), plus useful exclusions (not volume, not live). It does not name a specific sibling tool to prefer instead, which is the only thing separating it from a 5.

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