set

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

Beyond the annotations (which only declare idempotent, non-destructive, closed-world writes), the description discloses a real behavioral trait: mis-levelled values are silently ignored by PyMOL, and this tool escalates that to an error with remediation advice. That is exactly the kind of non-obvious behavior an agent needs. It stops short of saying whether unknown setting names error out or what the error payload looks like.

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?

Purpose is front-loaded in the first sentence, followed by exactly the constraint that matters most, with no filler. The second sentence is dense and slightly convoluted in its phrasing but every clause carries 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?

An output schema exists, so return values need no prose, and all three parameters are fully documented in the schema. Combined with the level model and the error-escalation behavior, an agent has enough to invoke this correctly without further reading.

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 100%, so the baseline is 3, but the description goes further by explaining the global/object/object-state/atom/bond level hierarchy that the `selection` parameter actually selects between. The concrete failure examples (cartoon_tube_radius on a residue range, ray_shadow on an object) give the parameter operational meaning the schema's one-line description does not.

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 first line gives a specific verb and resource ("Sets a PyMOL setting to a specified value"), which is unambiguous. It does not, however, distinguish itself from nearby alternatives such as set_symmetry or execute_pymol_command, so sibling differentiation is left to inference.

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 conveyed indirectly through the level discussion: the agent learns that values stored below a setting's level are ignored and that this tool will surface that as an error. There is no explicit when-to-use/when-not framing and no named alternative for cases like per-atom assignment (e.g. alter/alter_state), so guidance is implied rather than stated.

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