update_track

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

Annotations already declare readOnlyHint=false and openWorldHint=false, so the mutation profile is known; the description adds that a 'complete modifier stack' can be written, hinting that existing modifiers may be wholly replaced. It says nothing about whether 'patch' merges or overwrites, how expectedRevision conflicts behave, or whether requestId makes the call idempotent.

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?

A single dense sentence that front-loads the verb and the resource, then lists the payload options with no filler. Every clause maps to a distinct capability of the tool.

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?

This is a mutation tool with a free-form nested patch, no output schema, and four undocumented parameters, yet the description covers only the patch field names. An agent still cannot tell what target format is expected, whether the update replaces or merges current track state, or how revision conflicts surface.

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 description coverage is 0% and the 'patch' parameter is a free-form nested object, so the description carries heavy burden; it compensates by naming the accepted patch keys (keyframes, outOfRange, easeCurve, timeWarp, multiplierCurve, multiplierAmplitude, procedural controller, modifier stack). It leaves target, expectedRevision, requestId, and sessionId unexplained, so the compensation is partial.

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 ('Set track fields') and enumerates the settable fields, which tells an agent precisely what this mutates. It does not differentiate from close siblings such as set_keyframes, add_modifier, bake_track, or update_layer, so the boundary is unclear despite the clear purpose.

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?

There is no when-to-use guidance and no statement of when to prefer set_keyframes, add_keyframes, or add_modifier instead. The agent must infer the choice from sibling names alone, and the mention of 'keyframes' as a settable field actively blurs the boundary with set_keyframes.

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