create_experiment

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds nothing about the consequences of a destructive, non-idempotent create (e.g. duplicate experiments on retry) or any permission/state requirements, leaving the mutation semantics opaque.

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 single sentence is front-loaded with the verb and resource and contains no filler. It is efficient, though the brevity comes at the cost of the behavioral and usage context noted elsewhere.

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 destructive, non-idempotent mutation with four required parameters and no output schema, the description never states what happens on success, whether a version must be in a particular state, or how the new experiment relates to start_experiment. The agent is left to discover key operational details on its own.

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 four parameters including the 0-100 traffic range and platform enum. The description adds no additional meaning beyond the schema, which is the baseline for high coverage.

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 ('Create') and resource ('A/B test experiment for an app store version'), so the agent knows exactly what object is produced. It does not distinguish itself from siblings like start_experiment, stop_experiment, or get_experiment_results, leaving lifecycle placement implicit.

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?

There is no guidance on when to create versus start/stop/list an experiment, no prerequisites (e.g. the version must exist and be in an editable state), and no mention that creation is a separate step from starting traffic. The agent must infer the lifecycle from the verb alone.

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