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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=true; the description reinforces non-idempotency ('Each call creates another tutorial') and adds genuinely new scope context by clarifying that no video is recorded or rendered. It does not explain the destructiveHint=true flag, which is a notable gap for a create operation.

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 short, front-loaded sentences with no filler; the trigger condition and scope boundary come first. The return-value sentence is somewhat redundant given an output schema exists, which costs it the top mark.

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?

Covers purpose, scope limitation, and repeat-call behavior, and an output schema handles return values. The one unexplained item is why a create tool carries destructiveHint=true, which an agent might reasonably want clarified before invoking.

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% — all three parameters (name, projectId, defaultVoice) are documented with types, lengths and meaning in the schema itself. The description's mention of 'id, name, project and default voice' is about return values, not parameter behavior, so it adds essentially nothing beyond the schema. 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 tutorial to a project') and immediately delimits the scope against a sibling: 'it records the tutorial without recording or rendering a video. Not for adding a rendered video.' An agent can distinguish this from create_video without opening either 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 a clear triggering condition ('Use this when someone wants to add a new tutorial to a project') and an explicit exclusion ('Not for adding a rendered video'), which routes the agent away from create_video. It stops short of naming that alternative tool directly, so the routing requires one small inference.

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