blender_look_at

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

Annotations are present (readOnly=false, idempotent=false, destructive=false), and there is no contradiction with the description. The description adds genuine behavioral context by revealing the exact local-axis convention (-Z at target, +Y up), which is easy to get wrong. It stops short of explicitly stating that the object's rotation/transform is modified or what side effects may occur, though this is implied by 'Aim.'

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?

One compact sentence conveys the operation, coordinate convention, and supported object types without filler. Key constraints appear early, and the parenthetical detail is kept minimal and relevant.

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 low-complexity orientation tool with only three parameters, the description covers the operation, axis behavior, and supported use cases (cameras/spot lights). It does not describe return values, but response_format is already documented in the schema, and no output schema exists, making this a minor gap for a mutating 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 coverage is 67%; target and response_format already have descriptions, while object has only its name. The description adds some meaning by indicating object can be 'any object' and by clarifying the target as the aim point. It does not explain how object/target are addressed beyond what the schema already states, so the added parameter value is modest.

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 action: 'Aim any object along its local -Z axis at a target' and specifies the resulting up-axis (+Y), making the operation unmistakable. It also notes applicability to cameras and spot lights. It does not explicitly contrast with sibling transform tools like blender_set_transform or blender_apply_transform, so differentiation is implicit rather than named.

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 for cameras and spot lights' gives a useful context cue about intended use cases, implying this tool is for aiming those object types. There is no explicit 'use this when...' guidance, no mention of alternatives, and no 'do not use when...' exclusions, so the agent must infer when this is the right tool among many orientation/transform siblings.

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