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 real mechanism context — pairwise similarity matrix decomposed into eigenvectors, with leading-component coordinates returned per row — which is more than the annotations give. It still omits practical behavior such as minimum rows required, how gaps in aligned sequences are handled, or computational cost for large alignments.

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 moves from the operation to the model choices to the output, with no filler. It is dense but every clause carries information; a slight readability cost comes from cramming model variants into one sentence.

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 an output schema present, the description needn't describe return values, and it correctly focuses on the method and model selection. For a 5-parameter read-only analysis tool with full schema coverage, the remaining gap is only the absence of input preconditions and gap-handling behavior.

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 rows, model, components, _files and _subject thoroughly. The description adds only the alphabet-to-model mapping (protein vs nucleotide), which is also stated in the model parameter's own enum descriptions, so the marginal value is modest.

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 verb and resource — principal component analysis of the rows of an alignment — and spells out the similarity models (PID, BLOSUM62, PAM250, DNA) and the resulting per-row coordinates. It is clearly distinguishable from sibling analysis tools such as alignment_redundancy or alignment_agreement, 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: the closing clause 'so rows that cluster sit together' hints that this is for exploring row grouping, and the model enumeration implies alphabet-dependent choice. There is no explicit 'use this when…' or 'use X instead when…' routing, and no prerequisites (e.g. minimum row count) are stated.

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