crawl_stats

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful return-content context (daily series, breakdowns, robots.txt fetches, example URLs) which matters since there is no output schema, but it omits prerequisite state (logs must be imported), default date-range behavior, and result-size limits.

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?

A single front-loaded sentence that leads with the core action and then enumerates outputs; no filler or redundant phrasing. The semicolon-delimited list is dense but readable, though it reads slightly like a feature dump rather than prioritized guidance.

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 an 8-parameter, zero-required analytics tool with no output schema, the description does the important work of enumerating what comes back. It still leaves out the dependency on prior log import and any guidance on date-range defaults or data volume, which an agent needs to call it sensibly.

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%, so every parameter is already documented, making 3 the baseline. The description loosely maps its breakdown list to parameters such as response, bot_types, and host, but adds no format or interaction detail (e.g., how response interacts with top_urls) beyond what the schema already provides.

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 a specific resource and source: crawl statistics derived from imported access logs, with an enumerated list of metrics (requests, download size, response time) and breakdowns (response, file type, Googlebot type, purpose, host). An agent can distinguish it from siblings like performance_query or import_access_logs by the 'from your logs' framing, though no sibling is named explicitly.

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?

Usage is only implied: 'from your logs' hints that access logs must already be imported, but the description never states that prerequisite or says when to prefer this over performance_query or import_access_logs. There are no exclusions or alternative-selection rules.

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