admin_version_override_update

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

No annotations are provided, so the description carries the full burden. It discloses the mutation side effects (audit-logged, in-app blocker ratchets instantly without redeploy), the permission requirement (SUPER_ADMIN only), and the per-field independence so an agent knows one field won't clobber others. This is rich behavioral context beyond what is in the schema.

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 tightly-packed sentences with zero filler. The most important information (what it does, permission, and the three-state semantics) is front-loaded in the first two sentences, with operational specifics following. Every sentence earns its place, including the concrete consequence of ratcheting minOverride.

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 7-parameter admin mutation tool with no output schema, the description covers permutations thoroughly: all field semantics, the notify flag's escalation context, the SUPER_ADMIN gate, audit logging, and the no-redeploy ratchet behavior. The multiple-value union types (null/string/object) are all addressed for each relevant field.

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?

Though schema coverage is 100%, the description adds meaningful semantics beyond it: the three-state field behavior (override/clear/leave-as-is), the operational impact of bumping minOverride, and when notify should be passed true vs false. The example key format is in the schema but the description reinforces the critical override/clear/omit distinction that governs correct invocation.

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+resource+scope: 'Set or clear per-field version-gate overrides for one mobile platform.' This clearly distinguishes it from sibling admin tools like admin_version_overrides (a read/list) and admin_organizations/admin_users. It also specifies the permission level (SUPER_ADMIN only) and the per-field independence semantic.

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 explicit when-to-use guidance including the three-state field semantic (set string to override, null to clear, omit to leave as-is), which is critical for correct usage. It also explains concrete operational scenarios: ratcheting the in-app blocker via minOverride, and the notify parameter behavior for fanning out to affected users. The 'Default off — pass true for ratchets, leave false for silent corrections' instructs clearly when to toggle notify.

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