swap_clip

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

With no annotations, description carries full burden. It discloses async behavior ('Returns immediately'), render cost implication, hosted timeline syncing, and provenance storage. Minor conflict: opening says 'then re-render' but hosted mode defaults render=false; clarified later. Otherwise strong disclosure.

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?

Dense but structured with explicit LOCAL/HOSTED labels. Every sentence provides needed operational detail; no filler. Slightly long but warranted given two modes and 8 params.

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, so description should explain return/outcome. It states MP4 path for LOCAL and immediate return for HOSTED, but doesn't specify hosted return payload shape. Enough context for an agent to follow up with check_review_status. Overall complete for a complex tool.

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%, so baseline 3. Description adds value by grouping params into LOCAL/HOSTED sets, explaining conditional requirements (e.g., omit job_id to use env var), and linking asset/segment_id to suggest_clips output. Enhances schema semantics.

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?

Specific verb 'Replace' + resource 'cutaway' + asset source 'from suggest_clips'. Clearly distinguishes two operation modes (LOCAL vs HOSTED), making it distinct from siblings like swap_caption_style, trim_clip, render_project.

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?

Explicitly ties input params to project modes; names suggest_clips as prerequisite; tells when to use render_project for final render ('iterate freely, then call render_project once'). Gives clear decision path.

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