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

Annotations cover the safety profile (non-read-only, idempotent, open-world, non-destructive), and the description adds substantial context beyond them: required notifications:send scope, mandatory independent human approval of destinations/fields/stages/quiet hours, no priority bypass, and the concrete side effect profile ('May cause signed webhook notifications; never sends email'). This is exactly the extra context annotations cannot carry.

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?

Five compact sentences with the mutation action, constraints, and side effects front-loaded; every sentence carries weight. It is slightly telegraphic ('No priority bypass.' as a standalone fragment), which costs a little readability but not substance.

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 non-idempotent-appearing but idempotent mutation with no output schema, the description covers auth, approval, side effects, and recovery via receipts. It is incomplete on the concurrency parameters (revision/hash mismatch behavior) and on what state the rule ends up in after enabling, which an agent needs before calling it confidently.

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% across five required parameters, so the description bears the full burden, yet it only explains request_id semantics (reuse on uncertainty, retrieve receipt). Nothing is said about rule_id, expected_revision, expected_configuration_hash, or acknowledge_delivery, leaving the optimistic-concurrency contract and the delivery acknowledgement 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?

The description names a specific verb (enable) and resource (owned notification configuration), and adds scope that separates it from siblings: 'the exact owned configuration' plus 'start a fresh observation cycle'. An agent can distinguish this from pause_attention_notification_rule, preview_attention_notification_rule and save_attention_notification_rule without opening schemas.

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 real operational guidance for uncertain outcomes ('Reuse exact request_id for uncertainty; retrieve the receipt then read current state'), which is more than most, but it never names alternatives or states prerequisites such as previewing or saving the rule first. Usage is implied through the receipt/read-state workflow rather than stated as when-to-use vs when-not-to-use.

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