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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds genuinely new behavioral context — data provenance (stored provider facts vs. live model run), the fact that filters operate on different evidence sets (cited sources for domains, answer text for keywords), and the instruction to preserve null/unsupported values rather than fill them. It does not describe result shape, ordering, or pagination behavior, and there is mild tension with readOnlyHint=false for what reads as a retrieval tool, though nothing in the text asserts a mutation.

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 what the records are, followed by provenance and filtering semantics — very little waste. The closing sentence ('Preserve nullable evidence and unsupported dimensions') is terse and slightly cryptic, but it still carries operational 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?

With five parameters, a nested oneOf target, thin annotations and no output schema, the description supplies the two things an agent most needs: what a record contains (answer, cited sources, search references, brand entities) and how the two target kinds filter differently. Only the shape/ordering of returned records and the effect of limit remain unspecified.

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 carry the load, and it does for the hardest part: it explains that DOMAIN entries filter against cited sources while KEYWORD entries filter against answer text, clarifying the oneOf `target` array. The remaining parameters (limit, market, language, platform) are const- or enum-constrained with defaults and are not further explained, but they need little disambiguation.

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 resource — historical answer records with separate cited sources, search references and brand entities — so an agent knows it retrieves stored AI-mention evidence rather than computing something. It lacks an explicit verb ('returns/lists') and never names the adjacent siblings (nexscope_seo_ai_mention_history, nexscope_seo_ai_search_citation_sample, nexscope_seo_ai_model_answer_observation), so the boundary against those is inferred rather than stated.

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' implies a when-to-use condition and implicitly points away from live-observation tools, which is useful. However, no sibling is named and no explicit exclusion (e.g. use mention_history for trends instead) is given, so the agent must infer routing from the surrounding tool list.

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