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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world operation, so the bar is lower; the description still adds substantive context by defining null values ('no answers or no data yet') and the null/non-null contract for nextComparisonPage. The explanation of the selection ordering (named-not-you, then keyword ranker, vs/pricing page with the price-claim precondition) describes behavior no annotation or schema conveys.

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 purpose is front-loaded, but the second half is a single sprawling sentence nesting several ranking rules and parenthetical exceptions ('not one a content exclusion names', price-claim precondition) that is hard to parse in one pass. Every idea is relevant, yet the packing hurts usability and a bulleted or shorter phrasing would serve better.

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 an output schema handling return values, annotations covering the safety profile, and full parameter documentation in the schema, the description covers the remaining gaps: data scope limits, null semantics, and how nextComparisonPage is chosen. An agent has everything needed to call it and interpret the result without guessing.

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% and both parameters (languageCode, locationCode) are documented in the schema, so the baseline of 3 applies. The description only indirectly implies a market parameter via 'for one market' and never mentions language/location defaults, adding nothing the schema does not already state.

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 opening names the exact resource and scope: 'Your sites and each tracked competitor side by side for one market,' then enumerates the metrics returned (AI answer mentions, organic traffic/keywords, ChatGPT and AI Overview share). It is clearly distinguishable from get_competitor_ai_detail and list_competitors, though the verb is elided and the enumeration is dense enough that the core purpose takes a moment to extract.

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 a real scope boundary — 'These cover your own buyer questions, not the whole market' — plus the prioritization rules deciding which competitor nextComparisonPage recommends, which is genuine when-to-use context. What is missing is explicit routing against the named siblings (get_competitor_ai_detail, list_competitors, draft_competitor_page are listed without conditions selecting between them).

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