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

Beyond the annotations, the description discloses the critical behavioral trait that the rule is created disabled and does nothing until a person enables it, with the rationale that archiving or forwarding should not start from a chat message. It also discloses rule ordering semantics: rules run in order and a new rule goes last.

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?

The description is front-loaded with the most important behavioral fact ('THE RULE IS CREATED DISABLED') and then gives concrete workflow and sibling routing. Every sentence adds useful context: safety rationale, verification steps, ordering, and alternative tools.

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 complex mutation tool with no output schema, the description covers the crucial behavioral context: disabled-by-default creation, verification workflow, rule ordering, and related tools. However, it leaves the shape of the nested conditions/actions and parameters like match and stopProcessing to an under-described schema, so the picture is not fully complete.

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 only 17%, so the description needs to compensate for largely undocumented parameters. It only gives a conceptual summary of 'conditions' and 'actions' and does not explain match, stopProcessing, description, condition field/op semantics, or how action values work, leaving the agent to infer most parameter behavior from enum values alone.

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 states a specific verb and resource: 'Create a mail rule on the active connection', and explains that the rule consists of conditions and actions. It also explicitly names related sibling tools (testRule, setRuleEnabled, reorderRules, updateRule, deleteRule), making the boundary between creating and managing rules clear.

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 gives an explicit follow-up workflow: call testRule to preview what the last thirty days of messages would have caught, read the rule back, then ask whether to enable it with setRuleEnabled. This is unusually strong guidance about when and how to use the tool relative to alternatives.

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