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

Annotations already cover readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description still adds genuinely useful clarity with "Listing starts nothing," pre-empting the reasonable assumption that listing audits might launch them, and notes that existing results are returned alongside.

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 short sentences with no filler, and the important caveat about side effects is front-loaded at the end of the first thought and reinforced immediately. The category counts set output expectations without padding.

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?

With no output schema, the description must carry some return-value information, and it does by indicating the audit categories and the presence of existing results. A brief hint at result shape or pagination would make it airtight, but nothing essential for correct invocation is missing.

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?

There is a single optional parameter with 100% schema description coverage, so the schema fully documents the `store` argument. The description adds no further meaning about how to select a store, which is acceptable at this coverage level.

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 and resource ("List the audits Fudge can run for this store") and quantifies scope with the two audit categories plus existing results. It does not explicitly name or exclude the sibling get_store_audit_result, so the boundary between listing and fetching a result is only implied.

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?

"Listing starts nothing" signals this is a safe discovery step rather than a trigger, which implies when to use it. However, it never states when to prefer get_store_audit_result or start_store_builder instead, leaving the agent to infer the routing.

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