eyes_look_at

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

Annotations say readOnlyHint=false and destructiveHint=false, so the agent knows this mutates pose but is not destructive; the description adds genuinely new behavior: the ~30 degree eye limit (i.e., the result silently clamps for far targets) and the head-blend behavior. It does not say whether the pose is keyframed, whether it can be undone, or what a failed aim returns, which keeps it below 5.

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 dense sentence with the action front-loaded, followed by the two constraints that matter (joint limit, head blending). No filler, and nothing important is buried at the end.

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 4-parameter mutation tool with no output schema and solid annotation coverage, the description supplies the key behavioral facts an agent needs to call it correctly. What is missing (persistence/keyframing, undo, behavior when the target is out of reach) is secondary but not trivial for a pose-changing 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 75%, so the baseline is 3; the description goes beyond the schema by explaining the joint-limit consequence for 'target' and the 'head' blend semantics (share of turn taken by the head before the eyes). The 'eyes' enum (both/left/right) and 'figure' label are left to the schema and are self-explanatory, so no serious gap.

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 names a specific verb and resource (aims a figure's eyes) plus the full target set (camera, another figure, or a point), and states the scope constraint of the eye joint limits. No sibling in the list manipulates eye aim, so an agent can identify this tool from name plus description alone.

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?

Usage is implied by the described targets and by the note that head > 0 blends head rotation, but there is no explicit when-to-use/when-not-to-use guidance and no named alternative (e.g., a pose or head-rotation tool). Adequate for a narrow tool, but the agent must infer the boundary cases.

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