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

Annotations only establish readOnly=false, idempotent=false and destructive=false; the description adds consequential behavior they cannot express — that retrying incurs a new charge, that the existing Look, background media and loops are reused so prior work isn't re-billed, and the edge case where a pre-Look failure forces a fresh design. That is real cost and reuse semantics beyond structured fields.

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 tight sentences, front-loaded with the action and the cost warning, then reuse behavior, then the failure edge case. Every sentence carries distinct information with no restatement of the title or schema.

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 should ideally hint at what comes back (a new video id vs. reusing the same one) and whether the prior video record is replaced or coexists. It otherwise fully covers eligibility, cost, and reuse, so only that return-value ambiguity remains.

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?

There is one parameter (video_id) with 100% schema description coverage, so the schema already carries the meaning. The description adds nothing about the id's format, source, or behavior on invalid ids, so this is the standard baseline when the schema does the heavy lifting.

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 ('Run a finished, failed or cancelled video again') and scopes exactly which video states are eligible for retry. This implicitly separates it from create_lyric_video (new video) and cancel_video (terminal state), so an agent can route 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?

Clear usage context: this is for videos that already exist in a finished, failed, or cancelled state, and the parenthetical '(new charge)' warns of cost before invoking. No sibling alternative is named explicitly (e.g. when to prefer create_lyric_video), so it stops short of a 5.

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