query_runtime_state

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

Annotations already mark readOnlyHint=true, and the description reinforces this with 'Read' and clarifies important behavioral details: it requires launch_start first, empty results indicate success rather than error, the runtime shares the same GUIDs as edit-time, and it returns specific fields including rigidbody and element data when present. This is substantial beyond what annotations alone provide.

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 long but intentionally so, given the tool's complexity and the absence of an output schema. It is front-loaded with the core purpose, then covers return fields, filtering, pagination, use-case examples, and exclusions in a logical order with no filler 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?

For a runtime inspection tool with no output schema, the description is comprehensive: it explains prerequisites, return contents, filtering semantics, pagination metadata, success semantics, and alternatives. An agent has everything needed to decide when to call it and what to expect in response.

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% and each parameter already has a clear description in the schema. The tool description adds useful context beyond the schema, such as omitting both filters to page through every entity, the runtime using the same GUIDs, and the meaning of offset via nextCursor, though most parameter semantics are already well documented in the schema.

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 states a specific verb ('Read'), a precise resource ('LIVE runtime state of entities in the RUNNING Launch instance'), and distinguishes this from edit-time scene data by calling it the 'non-visual ground-truth read-back'. It also explicitly contrasts with sibling tools like list_entities and query_viewport_state, making its purpose unambiguous.

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 gives clear when-to-use guidance with concrete example questions ('did the ball actually move?', 'is the rigidbody simulating?'), and an explicit 'When NOT to use' section naming list_entities, pre-launch usage, and modify_entities/inject_input. It also states the prerequisite launch_start and explains when to use ids vs name vs neither.

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