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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), and the description genuinely adds behavior: idempotent calls, preservation of original input order, results retained in owner call history, a free owner-only retrieval endpoint, and the rule that missing values are not zero. These are real operational facts an agent could not infer from the schema, though the phrasing is dense and the actual intent-classification behavior is never described.

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?

Wait — the text is compact in length but poorly structured: fragmentary clauses, internal jargon like "Schema C1-1.0," and the one useful fact (retrieval endpoint) buried mid-paragraph. It is front-loaded with a restatement of the name rather than the value proposition, so every sentence does not clearly earn its place.

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 no output schema and zero parameter documentation, the description needs to say what a successful result contains (intent labels, counts, confidence) and what the input constraints are. Instead it describes plumbing (call history, retrieval URL) while leaving the tool's core result shape and semantics 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 parameter meaning, but it only hints at bounds with "bounded keyword inputs" without stating the 1–20 array limit or per-item constraints. The language parameter — a const "en" — is never mentioned, so English-only input is undocumented outside the schema's const value.

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 essentially restates the title ("Keyword Intent") and adds only opaque qualifiers like "explicit missing evidence" and "bounded keyword inputs." It never states what the tool actually produces — e.g. classifying keywords by search intent — and gives no signal distinguishing it from siblings such as nexscope_seo_keyword_metrics, nexscope_seo_keyword_categories, or nexscope_seo_keyword_expand.

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?

There is no when-to-use guidance and no named alternative among the many keyword tools in the sibling list. The only routing information is about retrieving results (nexscope_seo_call_result), not about when to invoke this tool, and the "seven-day source-freshness" clause is unexplained.

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