update_notification_policy

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

With no annotations provided, the description carries the full burden of behavioral disclosure, yet it only states the mutation verb "update." It fails to disclose the tool's key behavioral trait—patch-like semantics where null preserves current values—as well as existence requirements, validation behavior, or side effects. The schema's per-field notes ('null preserves current') reveal this, but the description itself stays silent.

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 a single four-word sentence with no wasted words, so it is certainly brief. However, the brevity reflects under-specification rather than deliberate economy—it is a restatement of the name rather than a structured summary of key facts.

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?

This is a high-complexity tool with a deeply nested body object (escalation steps, matchRules with nine rule types) and subtle partial-update semantics, yet the description provides no orientation toward these complexities. The output schema covers return values and the nested schema covers structure, but the description omits the semantic context that distinguishes update behavior from create behavior.

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% for top-level parameters, and the description adds nothing about what policy_id refers to or how the body payload should be structured. The nested schema is richly documented, which mitigates the gap, but the rubric requires the description to compensate when coverage is low, and it does not.

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 "Update a notification policy." is a verbatim restatement of the tool name (update_notification_policy) with no additional information, fitting the tautology category. It does not differentiate from sibling tools such as create_notification_policy, delete_notification_policy, or test_notification_policy, so an agent gains nothing beyond what the tool name already conveys.

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 provides no guidance on when to use this tool versus its siblings (create/delete/get/list/test_notification_policy). There is no mention of the partial-update semantics (null preserves current) that distinguish updating from creating, and no statement of prerequisites such as the policy needing to exist.

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