cross_validate

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

With no annotations, the description carries the full burden and does well: it discloses that strict raises 'validation_failed' on mismatch, that low_memory is effectively a no-op ('IDs are always read lazily'), and that sequences_file must be whitelisted and tree_file must live in an allowed read root. It adds real behavioral context beyond a bare statement, though it omits permission/auth details.

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?

Purpose is front-loaded in a single sentence, then parameters follow in a clean Args block. Every line adds information (the low_memory note is especially economical), with no 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?

Return values are covered by the output schema and all parameters are documented, but with 0 required parameters and two alternative tree inputs (tree_content vs tree_file) the description never clarifies that exactly one must be supplied or how they interact. That ambiguity is a real gap for correct invocation.

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 0%, so the description must compensate, and it documents all five parameters with meaning: tree_content as Newick/Nexus content, tree_file as a path within an allowed read root, sequences_file's whitelisting requirement, strict's default and failure behavior, and low_memory's parity-only status. Only the mutual exclusivity/required-choice between tree_content and tree_file is left unstated.

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 verb and resource: cross-validating tree tip labels against sequence IDs. An agent can tell what it does, though it does not explicitly distinguish itself from the sibling validate_tree (which likely validates tree structure rather than trees vs. sequences).

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?

The description never says when to use this vs. validate_tree, check_monophyly, or other validation siblings, and gives no prerequisites or exclusion conditions. The whitelist/read-root notes imply constraints but not routing guidance.

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