Create a guardrail or automation

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

Annotations already declare readOnlyHint=false and openWorldHint=true, and the description usefully adds that nothing is sent without confirm:true and that there is no server-side dry run. That is real added context. But it omits what a preview returns, whether the created rule is immediately active, and whether existing rules with the same name conflict.

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?

Two short sentences, front-loaded with the verb and resource and immediately followed by the write-safety constraint. No filler and nothing redundant.

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 write tool with a nested free-form body and no output schema, the definition is thin: the caller is left guessing what goes into 'definition' and what the response looks like on success versus preview. The critical dry-run gate is covered, which keeps it at a minimum-viable 3 rather than lower.

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 67%, so the confirm and idempotencyKey parameters are already documented in the schema and the description only restates the confirm behaviour. The nested body object is the weak point: 'definition' is an untyped empty schema and the description says nothing about its expected shape, and 'kind'/'enabled' interactions go unexplained.

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?

Uses a specific verb plus the two resource kinds it creates ('guardrail or automation') and names the endpoint, which is enough to distinguish it from rules_update, rules_delete and rules_list. Sibling differentiation is implicit rather than stated, 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?

The confirm gate effectively tells the agent how to invoke the tool safely, which is genuine usage guidance. However, it never says when to prefer this over rules_simulate or rules_update, nor does it flag that rules_simulate should be used to test a definition before committing it.

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