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

Despite annotations already declaring readOnlyHint, idempotentHint, and openWorldHint, the description adds substantial non-obvious behavioral context: 'Counts reflect SAMPLED diversity, biased by collection effort and rock availability, not true past diversity' — an interpretive caveat that prevents an agent from drawing false conclusions about the numbers. It also discloses return semantics ('The full bin set returns inline ... so you read the curve, the turnover, and the per-bin origination/extinction directly'), which is valuable beyond any structured field.

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?

The description is a single dense paragraph of about four sentences, and every sentence earns its place: function, required inputs, return semantics, and the sampling caveat. The core statement and example use case are front-loaded. It is appropriately sized for a 7-parameter tool, though slight paragraph breaks would improve scannability.

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 a complex tool with 7 parameters, an output schema, and no required fields in the schema, the description covers every decision an agent must make: clade selection (with the exactly-one rule), time bounding (two alternative strategies), count target, bin resolution, return semantics, and the interpretive caveat. Nothing an agent needs to invoke this correctly 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?

Schema description coverage is 100%, and the individual parameter descriptions in the schema are exceptionally thorough — max_ma/min_ma even explain which is the deeper-time versus nearer-to-present bound. The tool description reinforces the exact-one-of-base_name/base_id constraint and the interval-vs-range alternative, but these are already present in the schema. Baseline 3 is appropriate: the schema carries the heavy lifting.

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 names a specific verb and resource: 'Compute a diversity / origination / extinction curve for a clade across geologic time, binned by period, epoch, or age.' It anchors the function with a concrete user query ('answers "plot dinosaur genus diversity across the Mesozoic"') and the scope is clearly distinct from every sibling — none of the dataframe, taxon, interval, collection, or occurrence tools compute curves.

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 gives explicit input-routing guidance: 'Pass a clade-inclusive base_name (or base_id ... exactly one of the two)' and 'bound the span by a named interval ... or a max_ma/min_ma range.' It clearly separates the two alternative bounding strategies. It does not explicitly name a sibling to prefer in other cases, but the sibling set is functionally so different that an agent's routing is unambiguous.

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