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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the write/destroy profile is covered. The description adds the asynchronous execution trait, which is genuine extra context, but it omits that existing insights get overwritten and says nothing about how to observe completion. Value added, but incomplete for a destructive mutation.

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?

Three short sentences, front-loaded with the action and followed by the trigger condition and the async caveat. Nothing is wasted, though it is not maximally dense.

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, asynchronous mutation with no output schema, an agent still lacks guidance on polling/verifying the result and on the overwrite consequence. The description is adequate but leaves a meaningful operational gap.

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 100%, including the force-overwrite semantics and the superadmin customerId, so the schema carries the parameter burden. The description adds no parameter detail beyond scoping the target to 'a single run', making the baseline 3 appropriate.

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 and resource: 'Regenerate insights for a single run.' The word 'single' implicitly distinguishes it from the sibling batch_regenerate_insights, though that sibling is never named. Clear purpose without explicit sibling routing.

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?

Gives a clear when-to-use condition: 'when a run's insights are missing, incorrect, or need to be refreshed.' It does not name the obvious alternative (batch_regenerate_insights) or say when to prefer batch vs single, so it falls short of the top tier.

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