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

Annotations only declare readOnlyHint=false, so the description carries the real burden and does: it discloses irreversibility of consequence (a prompt edit "resets it to pending and drops its footage"), the exact ripple mechanics at each edge, and refusal conditions tied to locked tracks. This is consequence-level detail an agent could not otherwise infer.

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?

Front-loads the action, then the destructive-consequence warning, then ripple semantics, then the refusal — a logical order with no filler. The ripple paragraph is dense (nested parentheses, quoted enum values) and slightly heavy for a single tool, but every clause conveys operative behavior.

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 mutation tool with no output schema and partial annotation coverage, the description supplies what an agent needs to call it safely: side effects, data loss, ripple effects on secondary lanes, and failure/refusal handling with remediation. Nothing material is 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 80%, so baseline is 3; the description goes further by explaining the mechanism behind ripple_secondary "shift" (time lost at an edge is cut from every lane, gained time inserted, spanning clips split or stretched) whereas the schema only says "keeps clips, captions and stickers in sync." The prompt and duration_seconds parameters get no added semantics beyond the schema, which holds it back from a 5.

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 plus the exact editable fields ("Update a scene's prompt or duration"), which cleanly separates it from neighbors like studio.update_clip or studio.update_text_overlay. It never names a sibling tool by name (e.g. trim_scene vs. duration change), so differentiation is inferred rather than explicit.

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 ("changing the prompt of a generated scene") with a required agent action ("say so before doing it"), and offers an explicit alternative path when a shift is refused: "unlock it with lock_track, or pass ripple_secondary 'none'." It does not compare against duration-editing siblings such as trim_scene, leaving one routing question unanswered.

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