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

The readOnlyHint=false annotation already tells the agent this mutates state. The description goes further by enumerating the blocked operations and disclosing that the lock persists until explicitly unlocked — meaningful behavior well beyond the boolean annotation. It stops short of noting what happens when locking an already-locked track or whether the call is 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?

Four short sentences, front-loaded with the action and then the effect, the motivating use case, and the parameter scoping. No filler; slightly longer than strictly necessary for a two-mode toggle.

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?

With no output schema, the description carries the burden of explaining effect and scope, which it does well for a mutation tool: what is blocked, how long, and how far the lock reaches. Missing only edge-case behavior (already-locked tracks, return value).

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 50%, and the description usefully compensates by explaining the track/track_id interaction: the role enum locks every track of that role, while supplying track_id restricts the effect to one track. The `locked` boolean is only implied by "lock or unlock," leaving a small gap.

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?

"Lock or unlock a track" states a specific verb pair and resource, and the following sentence defines exactly what locking means (refuses move, trim, split, duplicate, delete). It is clear what the tool does, though it never explicitly contrasts itself with adjacent siblings such as studio.set_track_muted or studio.move_track.

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?

It gives a concrete when-to-use scenario: lock a finished voiceover before restructuring the picture so timing cannot drift. That is clear guidance, but no when-not-to-use or explicit alternative is named (e.g. mute vs lock).

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