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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description goes beyond that by disclosing the output shape (labelled path, residue-span runs, per-residue posterior) and a real runtime behaviour: the host loads the model once per session and the tool refuses by name when it has not been loaded. That failure mode is genuinely useful context an agent cannot get from 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?

Three sentences, front-loaded with the identity of the tool before the outputs and the prerequisite, and no filler. The middle sentence describing return contents partially overlaps the existing output schema, which is the only slight redundancy.

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 read-only analytical tool with a full output schema and fully documented parameters, the description supplies the remaining essentials: the algorithm, the residue-level decoding semantics, and the model-loading precondition. Only the routing relative to sibling membrane tools is missing.

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% and the decoding enum is already fully annotated in the schema (including relative cost of 'n-best'), so the description need not carry parameter meaning. It adds only the indirect notion of residue-by-residue decoding, hence the baseline 3.

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 states a concrete verb and resource — transmembrane topology of a protein — and names the specific method (HMM-TM 114-state HMM, JUCHMME, Bagos et al.) plus the three output artefacts, so an agent knows exactly what computation runs. It is clear and specific, but it never names or contrasts with the nearest sibling (protein_membrane_profile), leaving the agent to infer which membrane-analysis tool applies.

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 explicit guidance on when to choose this tool versus protein_membrane_profile, protein_signal_peptide or protein_disorder, all of which operate on the same input. The only conditional statement is a prerequisite (the trained model must be loaded), not a selection rule.

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