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

Annotations already mark readOnlyHint=false, confirming mutation. The description adds a valuable side effect: 'Creates a Saved Version before the change.' This goes beyond the annotations by disclosing that the operation snapshots the prior state, which is useful for rollback awareness. No contradictions.

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?

Two succinct clauses, with the primary purpose front-loaded and the important side effect stated in a follow-up sentence. No wasted words, and it conveys all necessary high-level information efficiently.

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 mutation tool with 8 parameters, nested objects, and no output schema, the description is adequate but leaves some gaps. It does not explicitly state that it is a partial update (only provided fields change), nor does it mention the response format or async behavior. The schema covers parameter constraints, so this is a moderate level of completeness.

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 coverage is 100% with clear descriptions for each parameter. The description lists 'active state, variants, traffic, and conversion goal,' which maps to is_active, variants, and goal_event_type/goal_event_filter. It adds marginal reinforcement but does not introduce information beyond what the schema already provides.

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 clearly states a specific verb ('Update') and resource ('native A/B test'), and enumerates the main fields it affects (active state, variants, traffic, conversion goal). This naturally distinguishes it from the create_ab_test, delete_ab_test, and read-only sibling tools like list_ab_tests or get_ab_test_stats.

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 verb 'Update' implies this is for modifying an existing A/B test given an existing test_id, and is not for creation (create_ab_test) or deletion (delete_ab_test). However, the description gives no explicit exclusion or alternative references, so usage guidance is only implied rather than stated.

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