run

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

Annotations convey it is not read-only, not necessarily idempotent, and not destructive. The description adds meaningful behavioral context beyond annotations: that runs are headless, bounded by frame budget or a condition, and that screen_image snapshots with inline=true return PNG content while a single inline frame may omit its output path. This details side effects and special capture behaviors without contradicting the annotations.

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 compact two-sentence summary that front-loads the core purpose and key behavioral distinctions. It covers a complex, multi-capability tool without redundancy. It could be slightly more structured, but it remains one dense, information-rich paragraph appropriate to the tool's complexity.

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 with an output schema and eight parameters, the description does well: it explains the central execution semantics, input scheduling, and snapshot return behavior (including the inline PNG nuance). It omits explicit guidance on side-effect-like details such as file outputs for video or temporary files, but the output schema covers return values and the annotations cover mutation hints. Almost complete, with only minor missing nuances.

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 carries the burden for explaining parameters. It effectively explains the overall execution model (frame budget/until condition), scheduled inputs, and snapshot capture including the inline PNG behavior. It does not detail every parameter such as random_seed, timeout, or stall_window_frames, but the description provides the framework in which those parameters make sense.

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 uses a specific verb ('Run'), names the resource ('a Pyxel script'), and specifies the execution mode ('headlessly') and termination conditions ('frame budget or until a condition holds'). It also enumerates the main capabilities (input scheduling, state/screen/video capture), which distinguishes it from siblings like validate, read_image, and diff_frames.

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 makes the tool's scope clear: running scripts headlessly in a controlled environment, suitable for generating snapshots while 'validate' likely just checks scripts. It does not explicitly name sibling alternatives or state when not to use it, but the context of being the only runner among siblings implies its usage. A small gap is lacking an explicit 'use X instead when...' statement.

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