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 real methodological context beyond that: baseline subtraction of the unstained tube, tube-to-channel matching, and per-row division by the tube's own detector. It does not state what is produced (a spillover matrix) or whether compensation is applied, 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 dense sentence front-loaded with the method and data source, with no filler. It reads as a run-on colon chain, which slightly hurts scannability, but every clause carries substantive information about the computation.

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 nine-parameter tool with nested objects, annotations, and an output schema, the description covers the algorithm end to end: per-tube statistic, baseline subtraction, tube-to-channel matching, and per-detector normalization. It leaves out only the nature of the returned object and any precondition on control quality, both of which are partially handled by the schema and its sibling quality-check tools.

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 all nine parameters, including the statistic enum and the stain_match enum. The description restates those choices ('median (or mean, or density mode)', 'by name distance or tube order') without adding syntax, defaults, or failure conditions beyond what the schema says, so the baseline of 3 applies.

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?

Names a specific verb (estimate spillover) and the exact resource it operates on (single-stained control tubes plus an unstained tube), plus names the underlying method (flowStats spillover()). It is clearly distinguishable from sibling flow-cytometry tools by the input data it requires, although it never names an alternative such as check_color_balance.

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 through the required data ('single-stained control tubes and an unstained tube from the project'), which tells an agent the experimental precondition but not when to prefer this over other flow tools. There are no explicit exclusions, no prerequisites about panel design, and no statement about what to do when controls are missing.

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