run_test_scenario

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

No annotations are provided, so the description carries the full burden. It discloses that the scenario is 'ordered' and operates against the running game, and mentions optional scene launching. However, it does not disclose important behavioral traits such as whether assertion failures affect the game state, whether screenshots are saved, or whether the scene launch replaces the current scene. This leaves a moderate transparency gap.

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 a single sentence of about 20 words. It is concise, front-loaded with the primary verb and object, and every word contributes meaning. No redundant or filler content exists.

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 tool as complex as this (with multiple step types, assertions, waits, and screenshots), the description is too sparse. It does not explain how assertions affect the scenario outcome, what happens on failure, whether the tool returns a pass/fail result or throws, or whether execution is synchronous. The schema covers parameter structure but not the runtime semantics. Given no output schema and no annotations, the description leaves critical gaps for an agent to correctly invoke and interpret the tool.

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?

The schema is rich and self-documenting, covering all step types and properties, but the description adds only a high-level overview by naming the step types and the optional scene_path concept. Since schema_description_coverage is 0%, the description does not fully compensate for low coverage, though the schema itself provides strong semantics. The description's mention of 'input/wait/assert/screenshot' and 'launching a scene' adds marginal meaning beyond the raw 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 clearly states the tool's purpose: 'Run an ordered input/wait/assert/screenshot scenario against the running game'. The specific verb 'Run', the resource 'scenario', and the enumeration of step types (input/wait/assert/screenshot) make it obvious what the tool does and distinguishes it from siblings like simulate_sequence (which likely handles only input sequences) or assert_node_state (single assertion). The optional scene launch adds further clarity.

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 provides clear context: it is used against a running game and can optionally launch a scene first, which implicitly defines when to use this tool. However, it does not mention alternatives or exclusions (e.g., when to use simulate_sequence or run_stress_test instead), so it does not fully meet the highest bar for explicit when/when-not guidance.

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