Infer a phylogenetic tree with bootstrap support

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

Adds significant context beyond annotations: always bootstraps, no skip option, cost linear in replicates, seed fixes both resampling and search. No contradiction with annotations (readOnlyHint, idempotentHint are consistent with deterministic computation).

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?

Description is concise (~80 words), well-structured with a bold purpose statement, a key behavioral note, and a clear Args section. Every sentence adds value; no 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?

Given the tool's complexity (phylogenetic inference), the description covers input requirements, model selection, bootstrap behavior, and cost trade-offs. Output schema existence handles return values, so no gap.

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?

All four parameters are well described despite 0% schema coverage: fasta (aligned, same length), model (examples, suggest select_model), replicates (range, cost linear, default advice), seed (fixes resampling and search). Adds meaning beyond type/name.

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 clearly states it builds a maximum-likelihood tree with bootstrap support, using a specific verb ('Build') and resource ('phylogenetic tree'). It distinguishes itself from siblings like select_model, compare_trees, and simulate_alignment by its core function.

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?

Provides guidance to run select_model first if model unknown, and notes that sequences must be aligned (this server does not align). Implicitly, this tool is for aligned sequences needing a tree with bootstrap. Lacks explicit when-not-to-use statements, but context is strong.

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