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

Annotations are sparse (readOnlyHint, destructiveHint, idempotentHint all false), so the description carries the behavioral burden. It explains that all conditions must hold for a match, that escalations always appear in the dashboard even without channels, and that the call returns the created rule. The reference to preview_escalation_rule implies the side effect of opening escalations against identities, adding meaningful context beyond the annotations.

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 front-loads the purpose and the mandatory confirmation step, then expands into condition semantics and channel behavior. It is long but every sentence adds necessary information for the complex condition object; there is no fluff or redundancy.

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?

With no output schema, the description states the return value ('Returns the created rule'). It also covers the condition grammar, the dashboard visibility rule, and the channel reference. The only unspecified context is the meaning of 'current customer', which is systemic, and the schema already documents effectiveAt, openAfterSeconds, and closeAfterSeconds. The description is complete for a create tool of this complexity.

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?

The schema describes properties only by type and a short label, leaving the condition object's semantics opaque. The description fully specifies the condition DSL: allowed operators (SCORE_LT, SCORE_LTE, etc.), categories, threshold range, badge slugs, and meaning of seconds for identity age. It also clarifies that channels are slugs and refers to list_channels, elevating the parameter documentation well above 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?

The description opens with a specific verb and resource: 'Create an escalation rule for the current customer.' It distinguishes itself from siblings by using 'create' and explicitly directing the agent to preview_escalation_rule as a pre-call alternative. The 'current customer' scoping adds precision.

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 gives explicit when-to-use guidance: 'Describe the rule and confirm with the user before calling; preview_escalation_rule shows how many identities it would open against today.' It also references list_channels for channel slugs, providing a clear path for required inputs. No exclusions are needed because the tool name and create nature already separate it from update/delete/get.

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