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

Annotations only declare a safe read-only, non-destructive, closed-world operation, so the description carries the burden of disclosing what is actually produced. It does this well by naming the two computed quantities, the three classification labels, and the secondary aggregation of windows into residue spans — context the annotations cannot supply. It stops short of saying how the class boundaries are drawn or what the segmentation thresholds depend on beyond the default.

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?

A single sentence that front-loads the method and then enumerates the two result tiers (per-window values, collapsed spans). There is no filler, no restatement of the title, and the clause structure maps onto the tool's actual output shape.

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 a fully described input schema and an output schema present, the description need not restate parameters or return fields, and it correctly spends its budget on the analytical contract instead. The one gap is that the Globular / Transmembrane / Surface-seeking labels are named but never defined, so an agent knows the vocabulary without knowing the decision rule. For a single-purpose read-only computation, that is a minor omission rather than a blocking one.

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 window, angle, minWindows and protein are all already documented with defaults and units in the schema. The description adds only the conceptual frame (sliding windows, segment collapse) and does not explain the helix-versus-sheet angle choice or the noise rationale behind minWindows. Baseline 3 is correct when the schema does the heavy lifting.

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 names a specific computation (Eisenberg hydrophobic-moment plot) applied to a specific resource (a protein), and enumerates the outputs: per-window mean hydrophobicity and moment, a three-way class assignment, and collapsed residue spans. That is far more concrete than a title restatement. It does not, however, differentiate itself from near neighbours in the sibling list (protein_profile, protein_topology, protein_signal_peptide), which an agent would need in order to pick between them.

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 by the method: an agent can infer this is the helical-moment / membrane-propensity view of a protein. There is no statement of when to choose it over protein_topology or protein_profile, no prerequisite (e.g. that the input must be a translated ORF), and no exclusions. The schema hints at wiring from translate_sequence, but the description itself offers no routing guidance.

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