morph_states

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

Beyond the annotations (destructive, non-readOnly, idempotent), it discloses the failure mode (deliberate refusal on ill-posed input), the exact precondition checked (atom i correspondence across states), and the licensing caveat that cmd.morph is Incentive-only while the topology check still runs on open-source PyMOL. That last point materially changes what an agent can expect from a call in a given environment.

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?

It is front-loaded with the highest-value insight (the refusal is the point) and the topology rationale follows logically. A few sentences are conversational ("The value here is the refusal, not the interpolation") and could be tightened, but there is no filler or repetition.

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?

With annotations covering the safety profile and an output schema covering return values, the description supplies the missing conceptual context: what a valid morph requires and the environment-dependent limitation. The only small gap is that it does not restate what object is produced, though the schema's name parameter default covers that.

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 name, steps, obj_name and validate_only are already fully documented, and the description does not add per-parameter meaning. Baseline 3 applies; it only indirectly motivates validate_only through the topology-check discussion.

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?

"Interpolate between states" is a specific verb+resource, and the immediate qualifier "refusing when interpolation is ill-posed" gives the tool a distinctive identity. It also separates this tool from the native PyMOL morph it wraps, so an agent understands this is a validated morph rather than a plain one.

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 gives a clear applicability test: use it when every state shares a topology (deformation-model ensembles like 3DFlex/DynaMight), not when volumes were reconstructed and modelled independently. That is effectively a when-not rule. It stops short of naming alternatives explicitly (e.g. mset/mplay/frame stepping), so it is a strong 4 rather than a 5.

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