deliver

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

With no annotations the description carries the burden and does well: it discloses the unreviewed-cut refusal, the confirm_unreviewed override, and that filepath actions refuse if the file no longer matches expected_sha256. It omits auth/permission needs and whether reformat/relink mutate or destroy source media.

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?

Three sentences, front-loaded with scope and guardrails, each earning its place. The trailing action list partly repeats the enum, which is the only real redundancy.

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 nine-action dispatcher with no annotations and no output schema, the description covers the key precondition and the sha256 safety net. It stops short of describing where exports land or what stems/reformat produce, which an agent would still have to discover.

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% and the args object already documents filepath, expected_sha256, and sha256 reporting; the description's action enumeration duplicates the enum. Baseline 3 is correct since the schema does the heavy lifting, though the sha256 guard is echoed usefully.

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 states a concrete domain (getting an edit out: export, reformat, relink, push) and enumerates the nine actions it dispatches, so an agent can tell it apart from edit/preview siblings. It is clear but the umbrella verb 'deliver' only becomes precise via the action list.

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 real usage rule: exports and push_to_fcp refuse a cut with no rendered preview of its current state, with the confirm_unreviewed=true escape hatch. It does not contrast when to use export_* versus preview or edit, so routing among siblings is left partly implicit.

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