rupa_lihat

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

Annotations already provide readOnlyHint=true and destructiveHint=false, so safety is known. The description adds valuable behavioral context beyond that: camera and lights are automatically set from the scene bounding box, ensuring framing regardless of object size, and the enforcement that the agent must read the image. This is beyond what the annotations convey and helps the agent understand side effects and limitations.

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 two sentences, front-loaded with the primary action and output, followed by the automatic camera/lighting behavior and the angle list. It is efficient and packed with necessary information without excessive fluff. The second sentence is long but logically structured.

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 tool with 7 parameters and no output schema, the description covers the core purpose, return type (PNG paths), and a critical behavioral requirement (read the image). However, it does not describe the output format beyond paths, nor does it explain several parameters. Given the moderate complexity, it is adequate but not fully complete.

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 low at 29%, with only mesin and ruang having descriptions. The description compensates for the most complex parameter, sudut, by listing named angles and the 'yaw,pitch' format in degrees. However, it does not clarify other parameters like fov, contoh, ukuran, or latar_tembus. Given the low coverage, the description partially compensates but leaves gaps.

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 tool renders multiple angles to PNG and returns their paths, with a specific verb and resource. It also lists supported angle names and a custom format, making the purpose unambiguous and distinct from any sibling that might just view or inspect a scene.

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 no explicit comparison to sibling tools or conditions for when to choose this over alternatives. However, it does offer behavioral guidance: 'BACA gambarnya sesudah ini, jangan mengaku selesai dari angka saja' (read the image, don't claim done from numbers alone), which tells the agent to actually visually inspect the output. This is useful but not a full when-to-use/alternatives discussion.

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