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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the additive/non-idempotent nature is partly structured. The description still adds non-obvious behavior: each call creates a separate source, and on a live agent the call is a silent no-op that returns publishUrl instead of erroring. It does not cover error conditions or failure modes, which keeps it short of a 5.

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?

Four sentences, front-loaded with the core action, then the additive caveat, then the live-agent constraint. Slight overlap between 'without editing or removing existing ones' and 'Each call adds a separate source' — both carry the same additive message, which is the only redundancy.

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 an output schema present, return values need no explanation, and the description covers the one genuinely surprising runtime behavior (live-agent no-op). Complete enough to call correctly; only failure/limit behavior is unaddressed, which is a minor gap for a 3-parameter create tool.

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 description coverage is 100%, with title, agentId and content each documented including length bounds and an example. The description adds only the general notion of 'text knowledge source' and does not elaborate on content format or sizing beyond the schema, so baseline 3 applies.

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 and resource ('Add a new text knowledge source') plus concrete examples of what counts as knowledge (FAQ answer, policy, product detail) and what the knowledge is for (agent search when answering visitors). This is clearly distinguishable from siblings like update_agent_instructions or create_agent.

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?

Explicitly scopes the tool to adding, not editing or removing, and gives a concrete when-not case: agents that are live on the web cannot be changed here. It even names the alternative path (retrieve publishUrl, take the agent offline first) rather than leaving the agent to guess.

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