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

With no annotations, the description carries the full burden. It discloses asynchronous ingestion, PENDING status, and the need to poll for READY. It also mentions the 50-page limit for url crawling. Missing details include error handling, idempotency, and potential failure modes, but core behaviors are transparent.

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?

Three sentences, no redundancy. The first sentence states the primary purpose, the second breaks down the two modes, and the third covers behavior. Information is front-loaded and every sentence is essential.

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 no output schema, the description adequately explains the invocation result (PENDING status) and next steps (poll list_knowledge). It lacks details on error states or timeouts, which would improve completeness for a moderately complex tool with two modes and async behavior.

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 description adds significant value beyond the schema: it explains that type='url' initiates a crawl with a page limit, and type='qa' stores a single pair. It clarifies conditional requirements (url required for url, question/answer for qa). This goes beyond the schema's basic property descriptions.

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 specifies two distinct types with concrete actions: url crawling (up to 50 pages) and qa pair storage. This distinguishes it from sibling tools like 'search_knowledge' or 'list_knowledge', which serve different functions.

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 explains when to use each type ('type='url' crawls a website; type='qa' stores a question/answer pair') and mentions polling with 'list_knowledge' for status. However, it does not explicitly contrast with sibling tools or state when not to use this tool, leaving some ambiguity for an agent.

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