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

Annotations already declare readOnlyHint and non-destructive, so the safety profile is covered; the description adds real behavior beyond that — all candidates share one topology (comparison is apples-to-apples, not jointly optimized) and results include Akaike weights. It does not mention runtime scaling or failure modes, but the output schema carries the return shape.

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 that leads with the action and follows with the mechanism and ranking output. It is dense but every clause (shared topology, criterion, weights) adds information; no 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?

For an 8-parameter tool with nested _subject and an output schema, the description supplies the essential conceptual context (shared topology, full sweep, criterion-based ranking). Minor gaps remain — no mention that input must be aligned or how candidates that fail to fit are handled — but nothing critical 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?

With 100% schema description coverage the schema already explains models, criterion, gamma_categories and include_invariant. The description adds only the 'model x rate-heterogeneity x invariant-sites' framing, which makes the candidate-count combinatorics explicit but largely restates what the parameter descriptions already say.

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 (choose the substitution model) and resource (ML phylogeny), then pins down the mechanism: fitting every candidate on ONE shared topology and ranking by AIC/AICc/BIC. The emphasis on a single shared topology cleanly separates it from tree-building siblings such as build_tree.

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 phrase 'for a maximum-likelihood phylogeny' places it as a pre-tree step, and 'every candidate is fitted' implies a sweep rather than a single fit. It never names an alternative tool (e.g. build_tree) or states when not to use it, so the guidance is contextual rather than explicit.

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