Set source text handling

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

Annotations only declare idempotency, yet the description discloses the key side effect (re-renders every finished clip) and the meaning of each return field (changed, needsRerender, rerendered, skipped), plus the skipped-clip edge case and remediation. This is disclosure well beyond the 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?

Single dense paragraph that front-loads the action and mode semantics before the return-value explanation. Efficient, though slightly crowded by packing enum restatement and return fields together.

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?

No output schema exists, but the description explains the returned object's fields and next steps, covering everything an agent needs to call and correctly follow up on this mutation. Complete for a 2-param idempotent setter.

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 100% and the enum is documented in-schema, so the description doesn't need to repeat it, but it reinforces the three mode meanings ('hide covers it, keep leaves it, always shows it') in workflow terms. Marginal added value over an already-complete schema.

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 ('Hide or keep') and resource ('text burned into the source video') scoped to 'the whole project', with the enum behaviors spelled out. An agent can distinguish this from clip-level or rendering siblings 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?

Explains the three modes and, importantly, tells the agent to follow with wait_for_project and to call rerender_clips once skipped clips finish. It lacks an explicit when-not-to-use statement versus rerender_clips/apply_framing, but the follow-up routing is clear.

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