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

Annotations only say readOnlyHint and openWorldHint, so the description carries the real burden and does well: it discloses the Clicky 31-day window, that Bing rolls up by week, that search_console rows include previous-period comparison, and that GA uses its own metric names rather than the tool's. It does not mention rate limits, quota, or upstream API failure behavior, which keeps it from a 5.

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?

It is one paragraph, front-loaded with the differentiator before the per-source detail, and each source sentence adds distinct information rather than restating the schema. It is dense and could be split into bullets, but no sentence is filler.

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 nine-parameter, four-source read tool with no output schema and thin annotations, the description covers the essentials an agent needs: which source yields what, source-specific constraints (Clicky's 31-day cap, Bing's weekly grain and single dimension), and what a search_console row contains. Remaining mechanics (paging, detail levels) are fully documented in the schema.

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 already 89%, so the baseline is 3, and the description earns above that by clarifying matching semantics ('page and query narrow to rows whose URL or query contains that text' – substring, not exact), that Bing only consumes the first dimension, and that Clicky's site may be a domain or site ID. The 'detail' enum's summary/rows/full progression and offset paging are left to the schema.

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 ('Raw rows for questions the report does not answer') frames it as the raw-data counterpart to the report, and each subsequent sentence specifies exactly what rows come back per source (search console dimensions, GA landing pages, Bing query/page by week, Clicky visits). An agent can distinguish it from seo_report, though the other siblings (seo_page, seo_research, seo_sites) are never named as alternatives.

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?

The phrase 'for questions the report does not answer' gives an explicit selection rule against the report tool, and the per-source clauses imply when each source applies. However, there is no guidance on when to prefer seo_page or seo_research, and no statement of what this tool cannot do.

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