skill_generate_playable_slice

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

With no annotations provided, the description carries the behavioral burden and does it well: it discloses that plan mode makes no network calls, that submit_assets launches paid external tasks only when confirm_spend=True, and that assemble creates Blueprint/AI/HUD/level/evidence/report outputs. It does not cover failure or rollback behavior, but the safety-relevant traits are present.

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?

The description is compact and front-loaded: a one-line purpose, a tightly structured mode breakdown, a KB pointer, and a useful example. It does not waste sentences restating schema fields, and the extra detail about payment gating earns its place.

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 multi-mode skill with an output schema and KB reference, the description covers orchestration, external payment side effects, and high-level outputs. It still leaves gaps around the unexplained session/content/run_pie parameters and how the evidence/report outputs feed into the broader workflow, so it is functional but not fully self-contained.

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%, so the description must compensate; it adds real meaning to mode, brief, task_ids, imported_asset_paths, and confirm_spend. However, content_path, session_name, and run_pie_seconds are left entirely to their names and defaults, leaving a noticeable coverage 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?

The opening line names a concrete verb-resource pair ('Plan, submit assets for, or assemble a generated playable slice') and the mode breakdown makes the three distinct workflows explicit. This clearly separates it from generic blueprint, spawn, or asset tools among the siblings.

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?

The description gives mode-by-mode guidance: plan is validation-only with no network calls, submit_assets is gated by TRIPO_API_KEY and confirm_spend=True, and assemble consumes completed task_ids or imported_asset_paths. It does not explicitly mention alternatives or exclusion cases, but the mode routing is clear and actionable.

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