get_capabilities

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

With no annotations provided, the description carries the full burden, and it explicitly discloses that the query is read-only and safe to call during stage startup. It also enumerates the major behavioral outputs, including active backend, feature flags, and unsupported arguments, which is meaningful context beyond the schema.

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 front-loaded with a clear purpose sentence and a follow-up sentence of concrete return categories. Every sentence earns its place, and there is no redundancy with the schema.

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?

An output schema exists, so return-value details do not need to be fully documented in the description. The description supplies the key semantic context: what kind of runtime facts are returned, that the call is read-only, and that it is available during stage startup. It is slightly light on when one might need this versus runtime status, but otherwise complete for a simple query 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?

Schema description coverage is 0%, and the description does not mention command_id or idempotency_key at all. Although these parameters are optional and generic, the description provides no guidance on their purpose, usage, or interaction with the tool's behavior.

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 ('Discover') and resource ('the live Isaac Sim MCP runtime') and clarifies it returns explicit limitations, making the tool's purpose clear. It does not explicitly distinguish itself from sibling introspection tools such as get_runtime_status, but the emphasis on capabilities and limitations provides adequate differentiation.

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 phrase 'works while the USD stage is still starting' gives a concrete timing context for when this tool is useful. However, the description does not state when to prefer this over alternatives like get_runtime_status or get_simulation_state, nor does it provide any 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.