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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's job is to add freshness and semantics, which it does well: 'Sampled daily: judge windows, not single days', a 14-day lookback for gap_candidates, and sitemaps 'read every Monday (7 days when not given)'. It stops short of stating rate limits or how the 90-day cap in the schema interacts with the default windows.

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?

Front-loaded summary line followed by a scannable per-view list, with no redundant restatement of the title. Some lines are densely packed with internal jargon ('intentSplit', 'domainCheck suspect', 'alsoNamed') that an agent can't resolve from this text alone.

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 eight parameters, no output schema, and no schema descriptions, the description should cover both view selection and filter semantics. It covers the former thoroughly but leaves five filter parameters and the return shape of each view undefined, which matters because there is no output schema to fall back on.

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 all eight parameters. It does an excellent job on the required 'view' enum, but five filters — cited, recommended, sentiments, engines, competitorId — appear only as bare names in parentheticals with no meaning (e.g. 'engines?' never explains the chat_gpt/gemini/google_ai_mode enum values, and 'competitorId?' gives no notion of where an ID comes from). 'days' is clarified only indirectly through window references.

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 opening line states a specific subject — how ChatGPT/Gemini/AI Overviews answer tracked buyer prompts — and the bulleted view list makes the seven distinct operations concrete. It never names a sibling tool (get_prompts, get_reports, get_activity) to say how this differs, so the differentiation is left to inference.

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?

Because this is a dispatcher, the critical usage decision is which view to pick, and each bullet supplies a condition: gaps for last week's rival-named prompts, gap_candidates for prompts missing the brand over 14 days, rival_pages for sitemap changes. It even gives sequencing advice ('Lead with unbranded (intentSplit)'). What's missing is guidance on when to use this tool versus get_prompts or get_reports.

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