get_scene_summary

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

Given that no annotations are provided, the description carries the full burden of behavioral disclosure. It clearly states the tool is a read-only 'get' operation with no side effects implied. It specifies the output content (object count, types, materials, camera, lights, render engine) and notes the token constraint, which sets expectations for output size. No contradictions with annotations exist since none are supplied.

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 concise and front-loaded. The first sentence establishes the purpose and tone, the second lists the return fields and the design intent. Every sentence serves a distinct purpose—clarity of intent, return content, and rationale—with no fluff. It fits in a few lines and is easily parsed.

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 zero-parameter, read-only summary tool, the description is complete. It states what it returns, the token budget, and the intended audience. Without an output schema, the description compensates by listing the return fields. There are no missing parameters or ambiguous behaviors that would hinder an agent from calling it correctly.

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 tool has zero parameters, so the schema provides no additional meaning. The baseline for 0 params is 4. The description does not need to explain any parameters; it instead explains the return payload, which is relevant context. There is nothing more to clarify about inputs, so a 4 is appropriate.

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 purpose: 'Get an ultra-compact scene summary (~200 tokens) for weak LLMs.' It specifies the resource (scene summary), the action (get), and the distinguishing feature (ultra-compact, token-bounded) that sets it apart from more verbose siblings like get_scene_info. The return fields are enumerated, leaving no ambiguity about what the tool delivers.

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 explicitly targets a use case: 'for weak LLMs' and 'Designed to fit in small context windows while providing actionable info.' This clearly tells an agent when to prefer this tool over more comprehensive scene queries. It does not explicitly name alternatives or when not to use it, but the context given is sufficient to guide selection.

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