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

Goes well beyond the annotations: atomic revision check, preservation of other groups and columns, cost ('Free'), required scope ('manage:settings'), and an unknown-outcome recovery procedure. The annotations cover safety/state hints, and the description layers on operational and permission context.

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?

Front-loaded with the confirm-gated action, then prerequisites, semantics, and recovery. Dense but every sentence adds actionable information; it is on the long side but not padded.

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 destructive, open-world mutation with no output schema, the description supplies prerequisites, auth scope, concurrency handling, change preservation, and failure recovery. An agent has everything needed to call it correctly and safely.

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?

With 0% schema description coverage the description must carry the params, and it does for the critical ones: expectedUpdatedAt ('null for an absent row') and clientRequestId ('stable UUID'), plus the confirm gate and change fields. It does not map the nested group keys or the tier enum values, so minor gaps remain.

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?

States a specific verb+resource ('save a narrow change to push preferences') and enumerates the exact scope (groups, tier, quiet hours). It clearly distinguishes itself from the sibling read tool soclo_notifications_preferences and from notifications_list/mark_read.

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?

Explicitly describes the preview-then-confirm flow ('Preview, then with confirm:true'), mandates reading soclo_notifications_preferences first, and gives a when-not-to-act rule ('do not retry automatically; reconcile first'). Alternatives and conditions are all stated.

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