preview_upload

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

With no annotations to lean on, the description carries the burden well: it discloses the dry-run default, the human-approval requirement for live writes, the refusal condition, and MD5-idempotency (safe re-runs). It stops short of explaining what `replace` destroys or why approval_id is needed.

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?

Two dense sentences, front-loaded with the action and target path, then constrained by mode/approval/refusal clauses. Dense jargon (spec.preview.shared, MD5-idempotent) is unglossed but every clause adds operational value.

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?

An output schema exists so return values need not be described, and the mutation's safety profile (dry-run, approval gate, refusal, idempotency) is fully covered without annotations. The main remaining gap is the undocumented `replace` parameter.

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% across 5 parameters, so the description must compensate. It meaningfully documents dry_run (default true) and implies locales and approval_id via the <locale> path and human-approval requirement, but never explains `replace` or the approval_id semantics.

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 (Upload) plus a precise resource path (fastlane/app_previews/<locale>/ → the editable version's IPHONE_67 preview sets) and the mechanism (asc CLI). An agent can distinguish this from sibling preview tools without opening the schema.

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?

Clearly sets preconditions and modes: dry_run=True sends nothing, a live upload requires human approval, and it refuses while preview_check has problems. It routes through preview_check as a gate, though it does not explicitly name a competing upload alternative.

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