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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that the result is flattened to one row per annotation with per-property distinct-value counts, but that is also captured by the existing output schema, and nothing is said about malformed/non-NeXML input or missing OTU annotations.

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 sentence that front-loads the verb and resource before the parenthetical detail about OTU fields and row granularity. It is dense but every clause carries information; only minor awkwardness comes from packing the field list and the aggregation into one long clause.

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, so the description needn't restate them, and it does outline row granularity. However, for a tool with nested _subject/_files parameters it leaves unclear whether the NeXML can come from a library record or must be inline text, which is a real gap given the parameter count.

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 nexml, _files and _subject parameters are already documented in the schema, and the baseline is 3. The description clarifies that the input is NeXML text, but does not explain the relationship between the raw nexml parameter and the _subject/_files record-reference form when both are present.

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 gives a specific verb and resource: read the taxon annotations out of a NeXML tree file, with a parenthetical enumerating the OTU properties (NCBI taxon, rank, parent taxon). That makes it distinguishable from siblings like tree_statistics, compare_trees, transform_tree or export_tree, though it never names any of them 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: an agent can infer you call this when you have a NeXML tree and want per-OTU metadata rather than tree shape or statistics. There is no explicit statement of when not to use it and no pointer to an alternative tool such as tree_statistics or compare_trees.

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