run_simulation

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly explains that the simulation runs as a background job, how analysis class is resolved (from analysis_stage, solver_type, analysis_type, or analysis_class), and that wait_seconds causes polling with a possible final status return. This gives meaningful insight beyond a simple 'run simulation', though it omits error handling or side-effect details.

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 three sentences, front-loaded with the core purpose and return value. It packs resolution logic, polling behavior, and follow-up tool guidance into a compact, well-structured paragraph with no fluff or repetition.

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?

The description covers the main workflow and references job_status/job_logs for tracking, and an output schema exists to document return values. However, it omits any mention of the required case_dir parameter and does not state prerequisites such as a validated case or existing project parameters, which are relevant for a complex simulation-launching 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 description explains the semantics of analysis_type, analysis_class, and wait_seconds, but does not mention the required case_dir or the parameters_file parameter. Since schema coverage is 0% and the schema itself provides only titles/defaults, the description partially compensates but leaves the most important parameter (case_dir) and the input file unexplained.

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 starts with 'Start a Kratos simulation as a background job and return its job_id', clearly identifying the action and output. It also distinguishes from sibling tools by directing 'Track progress with job_status/job_logs', making it unambiguous what this tool does relative to others.

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 conditional guidance such as 'If wait_seconds > 0, poll up to that long' and explains how to override analysis selection. It points to job_status/job_logs for subsequent tracking, implying when to use those instead. However, it does not explicitly contrast with validation tools like validate_case or list when NOT to use this tool.

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