mdrun_start

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

Annotations indicate a non-read-only, non-idempotent, non-destructive operation, and the description adds key behavioral details: the simulation starts in the background and returns immediately with a job ID. This adequately discloses the async nature. However, it could mention that the job continues after the tool returns, but overall it is transparent.

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 short sentence, which is efficient, but it could be restructured to include key parameter or behavioral notes without becoming verbose. It is front-loaded but lacks substance about parameters and workflow context.

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?

Despite having an output schema (not shown) and sibling tools for lifecycle management, the description fails to connect to the broader workflow (e.g., use mdrun_status to monitor). It does not explain the return value beyond 'job id' or provide any usage hints. For a 6-parameter tool with heavy reliance on parameters, completeness is poor.

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?

With schema description coverage at 0%, the description provides no explanation for any of the 6 parameters (tpr, ntomp, deffnm, nsteps, workdir, extra_args). It only says 'Start a simulation', which gives no insight into what each parameter means or how to use them. This is a critical 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 description clearly states the action ('Start a simulation'), the async behavior ('in the background'), and the immediate return value ('with a job id'). It distinguishes well from sibling tools like mdrun_status, mdrun_stop, mdrun_cleanup, etc.

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 explains that the simulation runs in the background and returns a job ID, but it does not explicitly state when to use this tool versus alternatives (e.g., when to use mdrun_status to check progress). There is no mention of prerequisites or the need to follow up with other mdrun tools.

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