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

Annotations already flag this as a non-idempotent, non-destructive write, but the description adds the failure mode (403 until the workspace is claimed) and the fact that the experiment lands in draft. Credential and account-state requirements are exactly the kind of context annotations cannot carry.

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?

Front-loaded with the action and state, then constraints, then preconditions in a logical order. It is dense but every clause carries a real rule; the weight sentence is slightly run-on but still parses cleanly.

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 5-parameter creation tool with no output schema, it covers the essentials: validation constraints, required credential, and workspace-claim gate. It could note what the call returns (e.g., the draft experiment identifier) since no output schema exists to cover that.

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%, so baseline is 3. The description earns above baseline by stating cross-field constraints the schema cannot express: weights must be consistent across variants, relative values for two variants versus whole percentages summing to 100 for more, and one variant must be the control.

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?

Opens with a specific verb, resource and resulting state: "Create a price experiment in draft." That cleanly separates it from list_experiments, get_experiment_definition and propose_experiment_variant. It never names a sibling explicitly, so it stops short of a 5.

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 concrete preconditions (Last Price credential, claimed workspace, self-registered sandbox key gets a 403) and structural requirements (2–10 variants, exactly one control). It does not contrast with alternatives such as propose_experiment_variant, so it lacks explicit when-not guidance.

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