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

Beyond the annotations, it discloses critical behavioral traits: project-scoping via project_id, duration-preserving semantics (no overlap or timing change), the default scope behavior, the result's landed/skipped counts, the project identity return, and the unsupported crossfade path. The '45 whips' anecdote adds operational context. No contradiction with annotations.

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?

The description is long but well-structured and front-loaded: scoping first, then semantics, then the critical jump-cut warning, style catalog, duration guidance, and unsupported operations. There is no filler; even the anecdote carries decision-relevant context. It could be trimmed, but the density is justified by the domain complexity.

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 5 parameters, no output schema, and subtle scope semantics, the description is remarkably complete. It covers project-scoping, style selection, duration constraints, removal via 'none', the landed/skipped result reporting, and the unsupported crossfade case. An agent has the context needed to invoke it correctly and report back accurately.

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 60%, leaving style and duration_s undocumented in the schema. The description compensates by explaining each style's visual effect, duration range with default and style-specific recommendations, and 'none' removal semantics. It reinforces the scope parameter and references the project identity return. It doesn't add detail for motion_motif, but that param has a schema description.

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?

The description clearly identifies the tool's function: applying duration-preserving transition effects at specific junction types (scene changes and inserts), with an explicit catalog of styles. It distinguishes itself from the many set_* siblings by focusing on junction categories and scope. The exact 'set' verb is implied rather than stated up front, but the meaning is unambiguous.

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?

The description provides explicit when-to-use guidance: default to scope='scene', pass scope='every_cut' deliberately, and report the landed/skipped junction counts rather than cut count. It warns of the concrete failure mode with jump cuts after cut_silences and explicitly states that crossfades are unsupported, so the agent knows to offer alternatives. This is model guidance.

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