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

Annotations already declare readOnlyHint=true and openWorldHint=true; the description adds substantial behavior beyond that: async semantics (status:'running' → poll get_task_results), streaming chunks, results persisted as citable Data records with a line index, and the mdOrHtmlDownloadUrl ?type=md→?type=html swap. It also explains clamping of maxWaitSec rather than honoring oversized values. No contradiction with annotations.

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 with purpose, then usage, then operational details in a logical order. It is long, but the tool is complex and most paragraphs earn their place; the main cost is mild redundancy — the prose inventory of question types partly repeats the five examples and the sources enum in the schema.

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?

Complex tool (nested request objects, five source enums, async polling, streaming, download links) with no output schema, so the description must explain returns — and it does: summary plus line index, Data records with mdOrHtmlDownloadUrl, streaming.chunks[], and the running-status path. Coverage of the trends source's three limits appears both in schema and description. Nothing an agent needs to call or follow up on this tool is missing.

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 coverage is 100% with richly described parameters, so the baseline is 3. The description adds value beyond the schema: it instructs the agent to speak in plain language and avoid syntax (directly shaping query/options), explains that requests and sources run in parallel, and clarifies the isResearch trade-off in operational terms. A modest but real increment over the schema's own descriptions.

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?

Opens with a specific verb+resource — 'Answer questions about search visibility and search demand' — and enumerates the exact data kinds (keywords, rankings, links, domains, trends). It explicitly names the sibling tools it is not (advanced_web_fetch for page content, advanced_web_search for current posts), so an agent can distinguish it from all six siblings without opening schemas.

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?

Gives an explicit 'Use when' test ('how a site or a market performs in search rather than about what a page says'), a 'Not for' section naming the alternatives, concrete example queries, and even routes follow-up behavior to read_collected_records/grep_collected_records. Nothing about when to pick this tool is left to inference.

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