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

Goes beyond the annotations by disclosing provenance (stored historical facts, not a live run) and the asymmetric filter semantics — domains match cited sources, keywords match answer text — plus a warning that evidence is nullable and some dimensions unsupported. That is exactly the kind of context annotations cannot carry. Minor gap: with readOnlyHint=false the description never explains why a database read is flagged non-read-only.

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 compact sentences, purpose front-loaded, no filler. 'Preserve nullable evidence and unsupported dimensions' is slightly cryptic phrasing but is short and carries a real instruction.

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 6-parameter tool with a nested discriminated union and no output schema, the description covers provenance and filter semantics but leaves platform/language constants, month-range expectations, and result shape unaddressed. Adequate, not complete.

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% at the top level, so the description must compensate; it does partially by explaining that DOMAIN entries filter on cited sources and KEYWORD entries filter on answer text, which is the key distinction in the oneOf union. It says nothing about platform (google vs chat_gpt), the market/language constants, the YYYY-MM month format, or the 10-target cap.

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?

States what is returned (monthly absolute mention counts) and where it comes from (the provider's historical database), which implicitly separates it from the sibling series nexscope_seo_ai_mention_deltas / _new_lost / _records. It never says plainly whose mentions (AI answer mentions for the supplied targets) or that it returns a monthly series across fromMonth..toMonth, so the verb is missing, but the resource and scope are identifiable.

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 a real selection cue against live-model siblings such as nexscope_seo_model_answer_observation, but there is no explicit when-to-use statement, no mention of alternatives by name, and no prerequisites or limits described.

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