knowledge_base_discover_website

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

The description does not disclose that this initiates an asynchronous process, that it may take time, or that it changes state (since readOnlyHint=false). It does not mention what happens to discovered URLs or whether the agent should poll for status. The only hint is 'start crawling' which implies a long-running operation, but it lacks any detail on expected behavior or side effects.

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?

The description is a single, concise sentence that conveys the core action. It is front-loaded and avoids unnecessary detail. While it is very brief, it is not padded with fluff, and the structure is acceptable for a simple action verb.

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?

This tool lacks an output schema, so the description must explain what the tool returns or what to expect after invocation. It does not mention that the crawl is asynchronous, that status can be checked via knowledge_base_get_crawling_status_for_latest_operation, or what the 'option' parameter (Exact, Path, Domain) means. The description is incomplete for a tool that initiates an async process and has no other explanatory context.

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?

The input schema already documents all parameters with descriptions (URL as string, option as enum, locationId with default, knowledgeBaseId as string). The description adds no additional meaning beyond the schema; it only repeats 'training' which is already implied by the knowledge base context. With 100% schema coverage, the description provides no extra semantic value.

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 'Start crawling and discover pages for training' clearly indicates an action to initiate a crawl for a knowledge base's training. It distinguishes from sibling tools like knowledge_base_train_discovered_urls (which trains after discovery) and knowledge_base_get_crawling_status_for_latest_operation (which checks status). However, it does not explicitly mention the knowledge base context, though the name and required knowledgeBaseId parameter make it clear.

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 description provides no guidance on when to use this tool versus related tools such as knowledge_base_train_discovered_urls or knowledge_base_get_crawling_status_for_latest_operation. It does not mention that this is the first step in a crawl-train workflow, nor does it state prerequisites like creating a knowledge base first. No differentiation or workflow context is provided.

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