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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false), so the bar is lower. The description usefully adds that the model is run locally and that V2/V3 succeed the published V1 network, but it says nothing about determinism, runtime on long sequences, or how the threshold-bearing output should be interpreted.

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 front-loaded sentence that starts with the actual deliverable rather than the tool name, with the citation kept in a parenthetical. It is dense with jargon (bidirectional LSTM, consensus of predictors) but nothing is strictly redundant.

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 9-parameter tool with a nested _subject object, it is adequate because the schema and annotations carry most of the load and an output schema exists. Still, the description never indicates what the result looks like conceptually (per-residue scores plus called IDRs) or that the advanced threshold/IDR parameters change that call, leaving the most consequential behaviour to the schema.

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 schema already explains protein, version, threshold, convert and the four IDR-calling knobs. The description adds only marginal meaning, mainly historical framing for the version enum ('V2/V3 the lab's successors'), which the schema already labels as legacy/current.

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 output ('per-residue intrinsic disorder') and names the engine and its provenance (metapredict, Emenecker et al. 2021, bidirectional LSTM consensus), which implicitly separates it from the model-agnostic sibling protein_disorder. It never explicitly names a sibling or says how it differs from protein_profile, protein_signal_peptide or scan_protein_domains, so differentiation is left to inference.

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 when-to-use guidance at all: no statement of which inputs qualify, no prerequisites, and no pointer to protein_disorder or protein_signal_peptide for overlapping questions. An agent reading this alone cannot tell why it would pick metapredict over the sibling disorder tool.

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