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

Annotations already declare destructiveHint=true, non-idempotent, non-read-only. The description adds genuinely new behavioral detail: the batch is a single atomic undo step, it returns what changed or the failure reason plus the new timeline, times are in seconds, and measurement-only ops (loudness, scopes) also return data here. It does not cover permissions/prerequisites, though the confirm gate is documented in the schema.

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 dense sentences, each carrying distinct information: operation model, atomic undo semantics, return behavior, and time/id conventions. Front-loaded with the core action; no 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 complex batch-mutation tool with no output schema, it covers return values, atomicity, units, and id provenance. A little more on failure modes or auth requirements would fully close the gap, but what is present is sufficient to invoke it correctly.

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 67%, and the opaque 'args' object has no schema description. The description compensates by explaining that args follow ops from list_edit_ops, that time args are in seconds, and that project ids come from get_project (schema says list_projects/create_project). This meaningfully disambiguates the nested action payload.

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+resource: runs one or more edit ops from list_edit_ops in order, as one undo step. It distinguishes itself from siblings by naming list_edit_ops as the source of ops and get_project as the source of clip ids, so an agent knows this is the executor rather than the enumerator.

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?

Tells the agent the workflow: fetch ops from list_edit_ops and clip ids from get_project before calling. It gives clear context for how to use it but does not explicitly state when-not to use it versus other edit paths (e.g., create_project or editor tools).

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