constraint_look_at

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation risk is known. The description adds the core runtime behavior (continuous facing of target) and the effect of keepOffset, but it does not disclose what happens to existing constraints, whether the constraint is appended or replaces one, or what error conditions may occur. This is acceptable but not richly transparent.

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 short, front-loaded with the action and result, and includes only relevant modifiers. The bilingual duplication adds length but is purposeful for a mixed-language API; there is no filler or unrelated information.

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 simple constraint tool, the combination of the description and fully-covered schema gives an agent what it needs to invoke the tool: target is required, objects defaults to current selection, and optional modifiers are explained. It lacks edge-case behavior such as invalid target handling or effects on existing constraints, but no output schema exists and the operation is straightforward.

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 100%, so the schema fully documents target, upNode, objects, and keepOffset. The description primarily restates upNode and keepOffset in prose without adding new precision such as defaults, coordinate-space details, or interaction rules between parameters. This matches the baseline of 3 for full schema coverage.

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 ('Add') and resource ('LookAt constraint') and states the effect: 'the object always faces target.' It is immediately distinguishable from sibling constraint tools like constraint_position, constraint_orientation, constraint_path, and constraint_surface because it names the LookAt constraint type explicitly.

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 clearly conveys the intended use case—making an object always face a target—and mentions selectable behaviors (upNode, keepOffset). It does not explicitly contrast with alternative constraints or state when not to use it, but the context is clear enough for an agent to route correctly.

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