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

The description does add real behavioral context beyond the annotations - stale/historical data provenance ('Historical provider database facts, not a live model execution'), how filters are applied, and output-handling advice about nullable evidence. But that same 'historical database facts' framing explicitly asserts a pure read, while the annotations declare readOnlyHint=false, sending the agent contradictory signals about whether the call can change state.

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 short sentences, front-loaded with the resource and result type, then provenance, then filter semantics, then output guidance. Almost nothing is wasted, though 'Preserve nullable evidence and unsupported dimensions' is terse to the point of being cryptic.

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?

There is no output schema, no meaningful annotation coverage of behavior, five parameters including a nested DOMAIN/KEYWORD discriminated union, and two enum-ish parameters (platform, market) whose meaning depends on data scope. The description covers provenance and filter routing but leaves the platform choice, result limit, and returned field shape completely unexplained, which is not enough for an agent to call this confidently.

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?

Top-level schema description coverage is 0%, and the description only clarifies one thing: that DOMAIN targets filter on cited sources while KEYWORD targets filter on answer text. The other four parameters - limit (1-20), market (US only), language (en only), and especially platform (google vs chat_gpt, which fundamentally changes whose citations are returned) - get no mention at all, so an agent cannot tell from the description which platform's citation universe it is querying.

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 phrase 'Provider ranked cited pages and their independent aggregate metrics' names the resource (cited pages), the ordering (ranked) and the payload (aggregate metrics), which is enough to know it is a citation-analytics lookup rather than a live model call. However it is a noun phrase with no verb, and it never distinguishes itself from close siblings such as nexscope_seo_ai_top_cited_domains (domains vs pages) or nexscope_seo_top_pages, leaving the agent to infer the difference from the tool name.

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?

No when-to-use, when-not-to-use or alternative is stated anywhere: the description never says to prefer this over nexscope_seo_ai_top_cited_domains when you care about pages, nor over nexscope_seo_ai_search_citation_sample when you need individual citations. There is also no stated prerequisite about what a 'target' must contain before calling.

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