Physics MCP Server

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

With no annotations provided, the description carries the full burden. It effectively discloses key behavioral traits: this is a destructive operation ('destroy'), it frees resources to prevent memory leaks, and the Rapier service keeps simulations in memory until explicitly destroyed. However, it doesn't specify error conditions or what happens if the simulation ID is invalid.

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 well-structured with clear sections (purpose, usage guidance, args, returns, tips, example). Every sentence adds value: the first states the action, the second explains why it's important, and the tips provide practical LLM guidance. No wasted words.

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 destructive tool with no annotations and no output schema, the description does well by explaining the tool's purpose, when to use it, parameter meaning, and behavioral context. However, it could be more complete by specifying the exact return format or error handling, though the 'Success message' return note helps.

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 has 0% description coverage, but the description compensates by explaining the single parameter ('sim_id: Simulation ID to destroy') in the Args section. This adds clear meaning beyond the bare schema type. The example also shows parameter usage, though it doesn't specify format constraints.

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 specific action ('Destroy a simulation and free resources') and distinguishes it from sibling tools like 'create_simulation' and 'step_simulation'. It explicitly mentions the resource being acted upon (simulation) and the outcome (freeing resources), avoiding tautology.

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 explicit guidance on when to use this tool ('Cleanup when done with a simulation', 'Always destroy simulations when conversation ends or changes topic') and includes practical tips for LLMs. It distinguishes this as a cleanup tool versus creation or analysis tools in the sibling list.

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