Replay a stored or inline automation over the last N days of metrics (read-only)

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description's "(read-only)" merely restates them rather than adding context. It says nothing about what a replay produces (matched entities, would-be actions, per-day evaluation), whether inline definitions are persisted, or the 90-day ceiling. The only value-add is the HTTP endpoint path, which is not actionable for an agent.

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?

One short, front-loaded sentence with no filler, which is structurally sound. However, it is almost verbatim identical to the tool title, so the sentence spends its words on redundancy rather than on information, and the appended endpoint path adds no decision value.

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 tool has a very complex nested schema (conditions, action oneOf variants, scope hierarchy) and no output schema, so the description carries a heavy burden it does not meet for input construction. It is only marginally complete for purpose: an agent knows it is a read-only replay, but not what it gets back or how to shape the definition.

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% and the single "body" parameter wraps a large nested object whose sub-fields (scope.platform enum of hundreds of values, conditions, action variants, minSpendForEval) are entirely undocumented. "Stored or inline automation" faintly maps to the ruleId/definition split, and "last N days" maps to body.days, but nothing explains the semantics of the fields an agent must construct.

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?

"Replay a stored or inline automation over the last N days of metrics" gives a concrete verb (replay/simulate), resource (automation/rule), and scope (N days of metrics), which is far better than a bare name. It stops short of naming the nearest sibling (rules_run, rules_runs), so an agent cannot tell simulate from run without opening both schemas, but the parenthetical "read-only" hints at the dry-run distinction.

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?

The description never says when to choose this over rules_run, rules_get, or rules_detectAnomalies, nor any precondition (e.g., the rule must already exist when passing ruleId). The only implicit guidance is the "(read-only)" marker, which suggests a non-mutating dry run but is not stated as a selection criterion.

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