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

With no annotations provided, the description carries the full burden. It discloses that ingestion is asynchronous, the source starts as PENDING, and suggests polling list_knowledge for READY status. It also mentions the 50-page crawl limit and quota sensitivity. This is strong behavioral transparency, though it doesn't cover failure modes or authentication requirements.

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, front-loaded with the primary purpose, then details. It efficiently covers both modes, asynchronous behavior, and status polling without waste. Every sentence adds value.

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?

Given the tool's complexity (two modes, async processing, quota limits), the description covers the essential usage and behavior. It does not have an output schema, but it indirectly addresses return behavior by mentioning PENDING and READY statuses. It omits details like error handling or idempotency, but those are not critical for a basic invocation.

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 baseline is 3, but the description adds substantial value beyond the schema. It explains the conditional requirement that url is needed when type='url' and question/answer when type='qa', and it adds the 50-page limit and quota context. This clarifies the interdependent logic that the schema alone does not convey.

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 tool's purpose: 'Train the AI agent by adding a knowledge source.' It then distinguishes the two modes (url crawling vs. qa pair) and explains the scope of each. This differentiates it from siblings like list_knowledge (listing) and search_knowledge (searching) by focusing on the add action.

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 clear context on when to use this tool (to add knowledge) and differentiates the two types with specific triggers. It also instructs to poll list_knowledge for status. However, it does not explicitly mention alternatives or when not to use it, such as using manage_faq for FAQ management, which would further improve guidance.

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