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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description must carry nearly the whole burden. It usefully discloses that results are historical provider aggregates (not a live model run) and that nullable evidence and unsupported dimensions should be expected — real behavioral context. But it never explains why a pure-looking lookup is not read-only per the annotation, nor any cost/latency/auth implications.

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 declarative sentences, roughly 40 words, with the core identity stated first and the caveats following. Dense and low-waste, though the final sentence reads as an instruction to the caller rather than a description of the tool.

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 tool with four parameters, a nested oneOf, zero schema descriptions and no output schema, the description covers data provenance and nullability but omits what metric fields are actually returned and how the non-target parameters affect results. Adequate orientation, incomplete for correct invocation.

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 0%, so the description must compensate, and it partially does: "domain filters use cited sources and keyword filters use answer text" explains the semantic difference between the two DOMAIN/KEYWORD branches of the required `target` array, which the schema does not convey. It says nothing about market, language, platform, matchType, include/exclude, or the 10-item cap, leaving most parameters unexplained.

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 the resource ("AI target metrics from provider database aggregates") but uses jargon with no verb and never says what a "target metric" actually is or what the tool returns. It also does not distinguish itself from close siblings such as nexscope_seo_ai_target_comparison or nexscope_seo_ai_mention_records, which an agent would plausibly confuse it with.

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?

"Historical provider database facts, not a live model execution" gives implied usage context — use this for historical aggregates rather than current model behavior. However, no alternative sibling is named and no explicit when-to-use/when-not condition or prerequisite is stated.

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