ghl_kb_crawler_train

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

Annotations cover safety aspects (not read-only, not destructive), but the description adds no behavioral context beyond the basic action. It does not disclose whether the operation is asynchronous, how long it might take, or what happens to existing data. For a training/ingestion tool, this is a significant gap.

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 two sentences with minimal waste. The purpose is front-loaded. The endpoint detail is useful but could be placed in a separate field. Still efficient and easy to parse.

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?

The description lacks information about return values, error handling, or post-conditions. Given it is a training tool with nested parameters and no output schema, more context is needed to understand what happens after ingestion. The openWorldHint annotation does not compensate for this gap.

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 the schema already documents all parameters with descriptions and examples. The description adds no additional meaning to the parameters. Baseline of 3 is appropriate as the schema carries the load.

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 clearly states the action (train and ingest) and the resource (discovered website pages into knowledge base). It distinguishes from sibling tools like ghl_kb_crawler_discover by specifying 'train discovered pages' rather than discover. However, it does not explain what 'train' entails, slightly limiting clarity.

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?

No guidance is provided on when to use this tool versus alternatives. The description implies it should be used after discovery (by mentioning 'discovered website pages'), but there is no explicit when/when-not or reference to sibling tools like ghl_kb_crawler_discover or ghl_kb_crawler_list_urls.

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