Update Experiment

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

Annotations already supply idempotentHint=true and destructiveHint=false. The description adds behavioral detail by enumerating valid state, verdict, and decision values, and by stating that the updated experiment is returned. It does not contradict annotations, though it doesn't discuss side effects on unspecified fields.

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?

Three sentences, front-loaded with the main action, and every sentence contributes: behavior, allowed values, and prerequisite. No filler.

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?

The description covers the core behavior, valid state values, and required input, and says the updated experiment is returned. Given the rich schema with 100% coverage, it is sufficiently complete; only a little detail on what the returned object contains is absent.

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 the schema descriptions already cover all parameters, including enums and null-clearing behavior. The description reiterates the enums and the required-id constraint, adding marginal value beyond the schema.

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?

Description uses a specific verb ('Update') and resource ('PM experiment'), and clarifies the action by saying it advances state and records outcome. This clearly distinguishes it from create_experiment and list_experiments.

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 clear context that this tool updates a PM experiment and states a prerequisite: resolve the id via list_experiments. It explicitly notes only id is required, but does not mention exclusions or alternative update tools.

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