refine

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

No annotations are provided, so the description carries the full burden. It discloses the input requirements and the outputs (.lst summary and .res model), which is helpful. However, it doesn't disclose side effects—refinement typically writes intermediate files including potentially overwriting .res, .lst, .fcf, and log files—nor does it mention error behavior when input is invalid. The output description adds context but stops short of full behavioral disclosure.

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?

The description is two concise paragraphs. The first delivers the core purpose efficiently, and the second covers inputs/outputs. No filler or redundant phrasing. Slightly more could be added on parameters, but it's tight and front-loaded with the most important 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?

The tool has 5 parameters (0% schema coverage), multiple sibling tools, and an output schema. The description identifies the key inputs, outputs, and supported programs. However, for a computation-heavy tool with no annotations, it would benefit from disclosing expected runtime implications, file side effects, or common failure modes. The presence of an output schema lightens the return-format explanation burden, but the behavioral/parameter gaps remain.

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 0%, so the description must compensate. It explains what ins and hkl are (the .ins file and .hkl reflection data) through the prose. However, it doesn't explain program (beyond the CGLS mention), timeout, or basename semantics—these are named in the schema but their purpose isn't elaborated in the description. Partial compensation, leaving several parameters underspecified.

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 clearly states the tool runs least-squares structure refinement using SHELXL or CGLS via shelxt, with a specific verb (refine) and resource (structure). It distinguishes itself from siblings like solve (solving vs refining) and validate_ins, though it doesn't explicitly name these alternatives.

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 specifies prerequisites (complete .ins file with L.S./CGLS and HKLF instructions, plus .hkl data), which gives the agent clear context for when this tool is appropriate. It doesn't explicitly call out when NOT to use it, but the prerequisites effectively gate usage. It mentions the program parameter supports shelxl or CGLS via shelxt, which is useful guidance.

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