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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds meaningful behavior beyond that: the inventory is 'owner-bound' and 'approximate', drawn from public robots/sitemaps/seed links, and that cursor continuation operates on a frozen snapshot with no new fetches. These are real operational traits a caller could not infer from annotations alone.

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 sentences with the core purpose front-loaded and the continuation behavior placed second where it reads naturally. No filler, though the second sentence is doing double duty as the only usage guidance, which slightly stretches its role.

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?

An output schema exists so return values need not be described, and annotations cover safety, which reduces the burden. But for a 6-parameter tool with a nested scope object and zero schema coverage, the description leaves the agent guessing about pagination limits, path filtering, and subdomain behavior. It is adequate conceptually but incomplete operationally.

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?

With 6 parameters and 0% schema description coverage, the description carries the full burden but only touches the cursor (continuation semantics), the seed url, and sitemap sources obliquely. It says nothing about max_urls, page_size, or the scope object's query_policy, include_paths/exclude_paths, and include_subdomains. Most parameters remain unexplained in both schema and description.

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 description gives a specific verb (build/continue) and a well-defined resource (an owner-bound approximate URL inventory sourced from robots, sitemaps, and seed-page links). An agent can understand the output is a URL catalog rather than page content, which implicitly distinguishes it from crawl/scrape siblings. It stops short of explicitly naming or contrasting with those siblings, so it lands at 4 rather than 5.

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?

It provides clear guidance for one mode: cursor continuation reads the frozen snapshot and performs no new fetches, which tells the agent when continuing is cheap/non-destructive. However, there is no explicit when-to-use versus alternatives (e.g., web_crawl) and no statement of when a fresh build vs. a continuation should be chosen. Usage is implied rather than routed.

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