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 by structured data. The description adds the useful behavioral note that it operates without rebuilding the tree and lists the computed artifacts, but says nothing about cost, tree-size limits, or handling of malformed/polytomous trees. Given annotations carry the safety burden, this is adequate but not rich.

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 led by the verb, with the outputs enumerated before the closing rationale. It is dense but every clause carries content; the em-dash apposition slightly lengthens it without waste.

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 and 100% schema coverage, the description need not explain return values, and it still names the three output families helpfully. The one gap is that it never mentions the alternate _files/_subject record inputs, implying the tree must arrive as pasted or wired newick, which could mislead an agent holding a stored record.

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 schema already documents newick, _files and _subject in detail; the description only refers to 'a tree' generically. Baseline 3 is correct when structured fields do the heavy lifting and the description adds no format or wiring detail beyond them.

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 ('describe') and resource ('tree') and enumerates exactly what is produced: shape statistics (tips, height, balance, gamma), the lineages-through-time curve, and the patristic distance matrix. The phrase 'without rebuilding it' cleanly separates it from build_tree, and the enumerated outputs distinguish it from draw_tree/compare_trees.

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 implied rather than stated: the tool is framed as the way to inspect a tree you already have, and the closing clause hints the patristic matrix is what to compare against alignment distances. There is no explicit when-to-use/when-not guidance and no sibling named as an alternative for e.g. comparing trees or drawing them, so the agent must infer the routing.

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