Set Track States

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

Goes well beyond the annotations: it discloses all-or-nothing pre-validation ('if any target is out of range, unreadable or asks for a state this host cannot read and write ... nothing is changed'), a real host limitation (solo has no public ExtendScript API and is probed on the QE track), and the snapshot round-trip contract. These are exactly the failure modes an agent must anticipate for a mutating tool, and none of them are derivable from destructiveHint=false.

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 front-loaded: the core action and its atomicity caveat come first, then snapshot semantics. Every sentence carries information. It runs long for a description and the solo/QE parenthetical is heavy, but nothing is filler.

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 5-parameter tool with nested objects and an output schema, the description covers the essential behavior: batching, atomic validation, snapshot/restore, and the read-only degenerate case. Return values needn't be explained since an output schema exists. Minor gap: the expected_cep_target and expected_project_path guards are never mentioned, though the schema documents them thoroughly.

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 the baseline is 3; the description earns above that by adding meaning the schema doesn't fully convey — that the snapshot payload is itself a valid input ('a restore payload this tool accepts unchanged') and that omitting every state field converts the call into a read-only capture. It does not touch idempotency_key or the CEP/project-path guards, but those are exhaustively documented in the schema.

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 opens with a concrete verb+resource+scope: 'Set mute, solo and lock on several video or audio tracks of the active sequence in one host command.' The 'several ... in one host command' phrasing implicitly separates it from the single-track siblings (mute_track, lock_track, toggle_track_visibility) without needing to name them. An agent can tell what this does and at what granularity.

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?

Usage is implied rather than stated: batch state changes across tracks, or read-only capture when no state fields are supplied ('with no state fields at all it is a read-only capture'). There is no explicit routing advice against mute_track/lock_track for a single track, and no prerequisites (active sequence required) are stated. Adequate but leaves the agent to infer when this beats the one-track alternatives.

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