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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description earns credit for adding the versioning behavior ("Default returns current versions only") and the fixed set of verdict outcomes, which the annotations do not convey.

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 with the most important content—the metric shape and verdict—front-loaded, plus one short scoping sentence. Slightly list-heavy, but no sentence is wasted.

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, return values need not be explained, yet the description still names the verdict categories so an agent can act on them. Combined with readOnly annotations and full schema coverage, an agent has everything needed to call this correctly.

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 both parameters are documented in the schema (experiment_id, include_superseded). The description's "Default returns current versions only" aligns with include_superseded but adds no syntax, format, or identity details beyond what the schema already provides; baseline 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?

States a specific verb (read) and resource (controlled lift experiments) and enumerates the returned content: four raw counts, 95% intervals, controlled lift in points, and verdict. It is clearly distinguishable from get_results or get_receipts by content, though it never names a sibling it competes with.

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?

"Use this to read controlled lift experiments" implies the usage context but gives no when-not guidance and names no alternative among the 14 siblings. The agent must infer that get_proof is for lift experiments specifically while compare_runs/get_results cover other result shapes.

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