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

The annotations (readOnlyHint=false, idempotentHint=false) already signal this creates state, and the description usefully confirms it by disclosing the 25-second timeout, the query_job_id fallback, and that omitting chat_session_id starts a new conversation. That is real context beyond the annotations, but it never says the question/answer is persisted into chat history or what happens to the job if abandoned — material omissions for a non-idempotent, state-creating call.

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 compact clauses, front-loaded with the core action, then the async/timeout behavior, then the session default. No filler and nothing repeated from the name or title.

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?

With no output schema, the description correctly should explain returns, and it does — an answer with sources or a query_job_id. Combined with the schema's parameter docs, an agent has enough to call correctly; only the persistence/lifecycle of the resulting chat thread is left unstated.

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 60%, and the description adds genuine meaning for chat_session_id (the one high-value parameter left undocumented in the schema) plus the implicit source_ids hint via "with sources." With the majority of the remaining semantics already carried by schema descriptions, this lands at adequate rather than rich.

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?

States a specific verb+resource ("Ask a notebook a question") and immediately defines the output ("the answer comes from its documents, with sources"), which separates it from read-only siblings like read_knowledge_document or get_knowledge_chat. An agent can tell what this does without opening the schema.

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?

Gives the key operating condition — up to 25 seconds wait, otherwise a query_job_id to hand to get_knowledge_answer — which effectively names the follow-up tool and when to switch to it. It also clarifies the chat_session_id branch (new conversation vs. continuing one). It stops short of contrasting with get_knowledge_chat or explaining when to prefer a stateless question over an existing chat.

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