Modify atomic properties for selected atoms by applying assignments like b=0 or chain='B', enabling targeted updates to molecular structures in PyMOL.
Alters atomic properties in a selection
| Name | Required | Description | Default |
|---|---|---|---|
| selection | Yes | Atoms to modify. | |
| expression | Yes | Assignment over atom properties, e.g. ``b=0``, ``chain='B'``, ``resi=str(int(resi)+100)``. |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v1.5.1Input schema / properties / expression / descriptionAdded value: +"Assignment over atom properties, e.g. ``b=0``, ``chain='B'``, ``resi=str(int(resi)+100)``."Input schema / properties / selection / descriptionAdded value: +"Atoms to modify."v1.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is supplied. The description adds nothing beyond them: it does not warn that changes are permanent/not undoable, that new atoms cannot be created this way, or that the expression is evaluated per-atom. For a destructive mutation tool the description carries little of its own weight.
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 short front-loaded sentence with no filler, which satisfies conciseness. But brevity here reads as under-specification rather than economy — there is room for a clause on what is altered and how it relates to alter_state.
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 not be explained, but this is a destructive two-parameter mutation tool with an expression mini-language and a near-twin sibling. The definition omits the persistence/irreversibility warning and the alter vs alter_state distinction, which are exactly what an agent needs before invoking it.
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% and the expression parameter already carries illustrative syntax (``b=0``, ``chain='B'``). The description adds no further meaning about accepted property names or expression evaluation semantics, so the baseline 3 applies.
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 ("alters atomic properties in a selection"), so the general purpose is legible. However, it never says which properties are alterable or how this differs from the closely-named sibling alter_state, leaving an agent unable to distinguish the two from the text 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?
There is no when-to-use guidance, no prerequisites (e.g. that a selection must already exist), and no mention of the alternative tool alter_state or set. The agent must infer the routing decision entirely from the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.