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

Annotations already declare readOnlyHint=true, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description still adds useful context beyond that: it is limited to tenant data, it exposes gate results that gate a follow-up action, and it notes that agent-created workflows allow automatic trials by default. The trial-safety sentence is a little oblique, which keeps it from a 5.

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 purpose, then usage, then limits and example — a sensible order with no filler sentences. The 'Agent-created workflows allow safe automatic trials by default' line sits awkwardly between the purpose and the usage guidance, interrupting the flow.

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 read-only tool with no output schema, the description does name the returned facets (stage, gates, metrics, trial setting), which is helpful. But it leaves the optionality of both parameters unexplained and gives no hint of what a gate result or stage value looks like, so an agent may need to discover the response shape empirically.

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 0%, so the description must carry parameter meaning. It gives one example object with only workflowId ('{"workflowId":"invoice-flow"}') and never mentions experimentId or the relationship between the two — e.g. whether experimentId is required when multiple experiments exist on a workflow.

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?

The description opens with a specific verb plus the exact resource set: 'Read an experiment stage, gates, metrics, and effective trial setting.' That is concrete enough to separate it from experiment_request_trial and from the broader workflow_* read tools.

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?

It states an explicit trigger ('when a draft or dry run has an experiment'), an explicit exclusion ('Do not use when you need to start a trial'), and a conditional next step pointing at experiment_request_trial only when all gates pass. This is the full when/when-not/alternative triad.

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