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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine context by naming the Turner-2004 nearest-neighbor model and the returned representation (dot-bracket plus ΔG), but omits important behavior for a folding tool: pseudoknot handling, length limits, and whether DNA is folded with RNA parameters (it only says T read as U in the schema).

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 dense sentence, front-loaded with the deliverable (MFE dot-bracket + ΔG), with the model citation parenthesized at the end. No filler.

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, and the description still previews them. However, for a computational tool with a nested _subject record parameter, the definition gives no caveats about input limits, pseudoknots, or ambiguity handling, leaving gaps an agent could trip over on non-trivial inputs.

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 the baseline is 3. The description's only parameter-relevant contribution is the RNA/DNA framing of the sequence input; the meaning of _subject and _files is entirely carried by the schema.

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?

A specific verb+resource (minimum-free-energy secondary structure of an RNA/DNA sequence), plus the output format (dot-bracket + ΔG) and the energy model (Turner-2004). An agent can tell this is a folding computation rather than, say, a structure reader like read_structure or a guide-design tool like fold_guide, though it never names those siblings explicitly.

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 only implied: 'of an RNA/DNA sequence' suggests feeding a sequence to obtain a fold. There is no statement of when to prefer this over read_structure, read_structure_consensus, or fold_guide, and no preconditions such as reasonable sequence length or single-sequence input.

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