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 adds genuinely new context: the credential requirement and the claim-workspace gate that causes a 403 — an error mode the schema and annotations do not reveal.

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 purpose and return fields are front-loaded, and prerequisite constraints follow in two dense sentences with no filler. It is slightly compressed but every clause carries information.

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 no output schema, the description usefully enumerates what is returned per variant and the comparison to control. It also covers the two environmental prerequisites an agent must satisfy before calling. Nothing essential for correct invocation 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 experiment_key description already specifies the key format and where to find it (list_experiments). The description adds no additional param semantics, so this sits at the baseline for high-coverage schemas.

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 resource ('Read how an experiment is doing') and enumerates the returned metrics (views, conversions, conversion rate, revenue, comparison to control). It naturally separates itself from get_experiment_definition/list_experiments by framing this as performance data, though it never names a sibling explicitly.

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?

Clearly states prerequisites: a Last Price credential and a claimed workspace, including the 403 failure mode for sandbox keys. It does not say when to prefer check_variant_significance or get_experiment_stopping, so the alternative-selection guidance is only implied.

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