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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds context they cannot: the PREMIUM license gate, and a precise error contract stating the tool never raises a protocol error but returns {"error": ...} with fix guidance, making retry-after-correction safe. The one sentence restating read-only/idempotent is redundant with annotations but harmless.

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?

Purpose and PREMIUM flag are front-loaded, then input/output shape, then usage and error semantics — a sensible order. The inline input/output example is long and overlaps the output schema, but it earns most of its space by disambiguating the nested count convention.

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 single-parameter analytical tool with an output schema and rich annotations, this covers everything an agent needs: input shape, output shape, licensing, error behavior, retry safety, and sibling routing. No material gap remains.

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 coverage is 100% and the schema already documents the index-0-is-cohort-size convention and the 24-cohort cap. The description adds a concrete worked example that makes the positional convention unambiguous, going modestly beyond the schema rather than repeating it.

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 and artifacts ('Build a retention table and average curve from raw cohort counts'), which pins down the computation precisely. It also names the sibling it is not ('Not for a one-pass funnel (funnel_report)'), so the agent can route without opening any schema.

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?

Gives an explicit positive condition ('Use when each cohort has counts per period since acquisition') and an explicit exclusion with a named alternative (funnel_report). Nothing about selection is left to inference.

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