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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description goes further by disclosing that the supplied list fully replaces the existing one and that an empty list removes all access. That replacement/clearing semantic is the key behavioral fact an agent needs and is not derivable from annotations. It stops short of stating permission requirements or whether revoking a notebook affects in-flight conversations.

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?

Two short sentences, zero filler, with the core action stated first and the replacement caveat immediately after. Every clause carries information the agent needs.

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?

For a two-parameter mutation tool with no output schema and destructive annotations, the description covers what it changes and what happens when the list is emptied. Remaining gaps — ownership/permission requirements and any downstream effect on existing app answers — are modest but real.

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?

With only 50% schema coverage, the description must carry weight, and it does for notebook_ids by defining replacement semantics and the meaning of an empty array — the most consequential detail. It adds nothing for app_id beyond the terse schema note 'The app.', and does not explain that the entries must be the owner's notebook IDs or note the 200-item cap.

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 names a specific action (choose which notebooks) tied to a specific resource (an app's AI answer scope), which cleanly separates it from the read-only sibling get_app_knowledge_access and from policy tools like set_knowledge_redaction_policy. An agent can identify the operation 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?

Usage is only implied by the phrase 'an app's AI may answer from' — it is clear this configures an app's knowledge scope, but there is no explicit guidance on when to call it versus alternatives (e.g., inspect first with get_app_knowledge_access) and no stated prerequisites such as owning the notebooks or the app existing.

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