fragment

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

Annotations declare readOnlyHint=false and idempotentHint=false, implying a mutating operation, but the description calls it "loads" without disclosing that it creates a new object in the session. It also omits what happens on a name collision, whether the fragment is added to existing objects, or whether it can be undone. With non-read-only annotations, the description should carry more of this burden.

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 sentence with no filler, and the action is front-loaded, but the brevity crosses into under-specification rather than efficiency. A few more words on what a fragment is and what it produces would cost little.

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. However, for a tool that materializes a new object in a session with non-read-only annotations, the description is missing the side-effect and naming context an agent needs to call it confidently.

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% and the schema already supplies the semantics of the single parameter, including concrete examples ("benzene", "ala", "formamide"). The description adds nothing beyond that, 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?

"Loads a molecular fragment" gives a verb and a resource, but "loads" is ambiguous in a PyMOL context where the tool actually builds a small molecule from a built-in fragment library into an object. It does not distinguish itself from siblings like fetch_structure, load_structure, or fab, which an agent could easily confuse with it.

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 guidance on when to use this versus load_structure, fetch_structure, or fab, and no stated precondition (e.g. that the name must be a built-in fragment rather than an arbitrary molecule). The only clue is the example list buried in the parameter schema.

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