add_creator

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

With no annotations, the description carries real weight: it discloses the asynchronous pipeline (returns quickly, transcripts download in background, ready content is searchable immediately) and the cost/scope implication of full=True. It omits permission/auth requirements, deduplication behavior on repeat adds, and failure modes for an invalid handle.

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?

Front-loaded with the action, then the async behavior, then the full flag, then post-call instructions — a sensible order. Four sentences all do work, though "Tell the user the returned brain label and that more material keeps arriving" is agent-facing guidance that slightly blurs with the tool's own semantics.

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?

An output schema exists, so return values need not be explained, and the description covers the async model, the parameter tradeoff, and the follow-up message to the user. What is missing is edge-case behavior — repeat adds, invalid handles, and any rate or quota expectations for a long-running ingestion job.

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 0%, so the description must compensate and it does: handle is illustrated with both accepted forms, and full is defined precisely as "every video instead of the newest 30% plus the top winners" — semantics an agent could not infer from a bare boolean named Full.

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?

"Add a YouTube creator ... to the brain and start building it" is a specific verb+resource with concrete identifier formats (@handle or channel URL). It implicitly separates itself from the add_videos sibling by operating at channel level, though it never names that alternative explicitly.

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 makes the use case clear (onboarding a whole creator rather than individual videos) and explains the one branching decision, full=True vs the default 30% + top winners. It does not state when not to use it or what happens if the creator is already present.

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