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

With no annotations, the description carries the full burden, and it does add useful context: the tool is FREE, covers Base only, and returns settled/verified audits rather than pending ones. It omits how many records come back, whether results are paginated or time-windowed, and whether the agent should poll for a live stream — gaps that matter for a monitoring tool with zero annotation coverage.

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?

A single front-loaded clause with the trigger condition first and no filler — efficient. It is arguably too terse for a feed tool, since a second clause on return shape would have earned its place, but nothing present is wasted.

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?

Zero parameters makes invocation trivial, so the only real unknown is the return shape, and with no output schema the description should describe it — it does not say how many audits, over what window, or in what form. Coverage of chain, cost, and verification status is a helpful partial, but the response contract is left entirely to inference.

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?

The tool takes no parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description correctly implies the tool is callable without any input, consistent with the empty schema.

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 resource domain (verified on-chain settled token audits on Base) and implies a recency/stream view, but never states the actual operation — e.g. 'returns the most recent audits' — so the agent must infer that this is a list/feed tool rather than an audit-execution tool. It does not distinguish itself from siblings like aegis_token_audit or aegis_priority_audit by name.

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 'USE WHEN: Monitoring the real-time stream...' framing gives an implied trigger condition, which is better than nothing. However, there is no when-not guidance and no routing to alternatives, which matters here because several siblings (aegis_token_audit, aegis_priority_audit, aegis_preflight_bundle) could plausibly be chosen for audit-related needs.

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