Crawl a site

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

With no annotations, the description carries the full burden and does well: it discloses that the crawl is live, same-origin, breadth-first, robots.txt-respecting, capped at 200 pages, and that it mutates shared state by making the result the active dataset. It omits things like expected runtime, rate limiting, and failure behavior on unparseable or unreachable URLs.

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?

Two dense sentences with no filler: the core behavior lands first, then the cap and the escalation path. Every clause carries information an agent needs (scope constraints, side effect, limit, alternative).

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 no-annotation, no-output-schema mutation tool, the description covers what the crawl does, its constraints, its limit, and its effect on the rest of the toolset. It leaves out the shape of the result and any indication of how long a large crawl takes or how failures are surfaced.

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 100%, so url, maxPages, and ignoreRobots are already documented in the schema; a 3 is the baseline. The description only restates the page cap already expressed by maxPages' maximum and never mentions ignoreRobots, so it adds little parameter-level meaning beyond 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?

Specific verb+resource ('Crawl a website live') with concrete scope qualifiers (same-origin, breadth-first, robots.txt respected) and the side effect (result becomes the active dataset for the other tools). It also names the sibling load_export as the route for a different job, so an agent can distinguish it from siblings without opening a schema.

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?

Explicitly routes the full-site-audit-with-history/Search-Console case to the desktop app plus load_export, which is a clear when-to-use-this-instead signal. It does not address the smaller-scale alternative (e.g., using get_page for a single URL), so the guidance is strong but not exhaustive.

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