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

Annotations already declare this a safe read-only, closed-world operation, and the description goes beyond them by disclosing the underlying algorithm's parameterization: gap–gap and gap–residue columns are counted and a gap never matches, which materially affects results. The 4-row minimum is also surfaced, which is not enforced by the schema. Output format is covered by the output schema, so no deduction there.

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?

Front-loaded with the core operation, then the model options, then the behavioral caveats and the wiring hint — a sensible order. It is dense and the 'gap–gap and gap–residue columns counted, a gap never matching' clause is terse to the point of being cryptic, but no sentence is redundant filler.

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?

Given an output schema, full parameter descriptions, and read-only annotations, the description fills the remaining gaps: what the computation actually does, the row-count floor, alphabet support, and how to source the alignment. The generic `_files`/`_subject` plumbing is adequately documented in the schema itself, so nothing an agent needs to invoke this correctly 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 coverage is 100%, so the baseline is 3, and the description earns an increment by adding a constraint the schema omits: 'Needs 4 rows' gives a de facto minimum for `rows`, which has no minItems. It also restates model applicability (PID any alphabet, BLOSUM62/PAM250 protein, DNA nucleotides), which duplicates schema text, and says nothing extra about `components`.

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?

Names a specific technique and resource: principal component analysis over the pairwise similarity of alignment rows, with the similarity model choices spelled out. It does not name any sibling it competes with (e.g. build_tree, alignment_redundancy, genotype_pca), so differentiation is left to the reader's inference, but the operation itself is unambiguous.

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 real guidance on prerequisites ('Needs 4 rows') and on input wiring ('Wire alignedSequences from align_sequences'), which tells an agent how to obtain valid input. What is missing is when to prefer this over alternatives in a large sibling set — no statement of when PCA is the right analysis versus a tree, distance, or redundancy calculation, and no exclusion criteria.

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