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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds real context beyond that: it says the verdict is computed against whatever margin the caller supplies, that no margin is imposed authoritatively, and that the default is a labelled rule of thumb traceable to a tech note rather than primary literature. It does not discuss cost or performance, but the epistemic transparency is valuable.

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 core concept, which is good, but it runs long and the margin-authority/provenance discussion duplicates the schema's own margin description almost verbatim. That repetition is not earning its place, and the scholarly asides dilute the actionable content.

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?

For a complex nested-parameter tool with annotations and an output schema, the description supplies the conceptual model, the returned values, and the margin caveat, so an agent has what it needs to call it correctly. It is nearly complete, with only the absence of explicit alternative-routing as a gap.

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 schema already documents margin, stem_length, probe and conditions in depth; the description largely restates the same margin provenance and vendor disagreement that the schema carries, so it adds little semantic value beyond the schema despite the strong conceptual framing.

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?

States a specific verb+resource (check the Scorpion stem) and precisely what it computes: the stem-loop hairpin Tm versus the loop-target duplex Tm, framed as a relation between two structures. This distinguishes it cleanly from generic siblings like melting_temperature or screen_oligo_structure, and an agent can tell what it produces without opening the schema.

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 framing 'the design question is a RELATION between those two structures, not a property of either' implies when this tool is appropriate over a plain Tm calculation, and the margin discussion signals design-time use. But it never names an alternative sibling or states explicit when-not conditions, leaving the routing to inference.

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