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

Annotations already disclose mutation semantics (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds real value beyond them by stating the effect on downstream processing: mixing reuses saved clips and triggers no new video generation. It does not describe whether the choice can be changed afterward or what state follows, which keeps it from 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?

Two sentences, no filler, with the triggering state front-loaded so the agent can gate the call immediately. The second sentence carries a distinct, useful fact rather than restating the first.

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 2-parameter, no-output-schema choice tool, the description covers the precondition, the option set, the preview lookup path, and the side-effect profile. Nothing an agent needs in order to invoke it correctly appears to be missing.

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 only 50% (productionId documented, the choice enum is not), but the description compensates by explaining what each enum value means: A/B are instrumental options, 'none' keeps dialogue only. It also tells the agent where the preview links come from, which the schema does not.

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 (pick) and resource (instrumental option A/B or none) and frames it with the exact lifecycle state (

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 precondition ('when state is awaiting_soundtrack') and a concrete alternative ('none to keep dialogue only'), plus points to get_production → music.options for previews. It stops short of saying what to do if the state is not awaiting_soundtrack, so it is strong context rather than a full when/when-not map.

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