watch_simulation

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

With no annotations, the description must fully disclose behavior. It explains that the tool steps 'go' once per tick with a pause, and that it works but is pointless in headless mode. However, it does not explicitly state that it returns no data (unlike run_simulation) or mention any side effects. Still, the behavioral description is largely adequate and truthful.

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 two short paragraphs with the key point in the first sentence. Every sentence serves a purpose: stating the primary function, comparing with the sibling, specifying use cases, and noting headless mode. No fluff or 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?

Given the tool's moderate complexity (3 params, high schema coverage, output schema present), the description covers the essential behavioral and usage aspects. It explains the slow stepping, the pause, the headless caveat, and the target audience (demos, teaching). Lacking only a brief note on return value (likely nothing or a status), but not a critical gap.

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%, so baseline is 3. The description reinforces parameter usage (e.g., 'pause between steps' maps to delay_ms) but adds little beyond the already-detailed schema descriptions. For example, the schema already explains the 120-second constraint on delay_ms. No new semantic insight is provided.

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 opens with 'Run the simulation SLOWLY so a human can watch it in the GUI window,' clearly stating the verb (run), resource (simulation), and key distinguishing trait (slowness for human viewing). It contrasts with sibling 'run_simulation' by noting the speed and data-return difference, making the tool's unique role unmistakable.

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 explicitly compares with 'run_simulation' and gives clear usage context: 'use it for demos and teaching when the user wants to see the dynamics unfold live.' It also warns against headless mode: 'In headless mode it works but there's nothing to watch; prefer run_simulation there.' This provides direct when-to-use and when-not-to-use guidance.

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