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

The description does add real context beyond annotations (credentials/mandates required, no authority granted, backend status and JSON errors surfaced), which is valuable. However, it frames the operation as a read ('Read a single view', 'Shows proof events') while annotations declare readOnlyHint=false and destructiveHint=true, and it simultaneously claims it 'does not read or write an inbox'. This is an annotation contradiction.

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?

The text is disorganized and repetitive, listing the same proof-event categories three times (completed runs, receipts, callbacks, exceptions, handoffs) and burying the contradictory sandbox disclaimer ahead of any usable statement of purpose. It is not front-loaded around the tool's actual function.

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, open-world write tool with no output schema and an undocumented parameter, the description should clarify what gets affected and how to invoke it. Instead it leaves the destructive semantics unaddressed and surrounds the call contract with caveats and contradictions, so an agent cannot safely call it.

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 0% for the single 'mode' parameter, and the tool description never explains what 'mode' accepts or how to populate it. It only hints that an existing product POST body with 'documented mode, arguments, and required signed authority' is expected, leaving the parameter effectively undocumented.

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 by declaring the backend unavailable and the tool a sandbox that 'generates five example proof-event categories' and 'does not read or write an inbox', then immediately says 'Read a single view of completed runs...' and 'Shows proof events from live agent work.' These statements conflict, so an agent cannot tell what the tool actually does. No sibling tool is named or differentiated.

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?

There is no explicit guidance on when to use this tool versus the many sibling proof/receipt/relay tools (wever_proof-relay, wever_receipt-passport, wever_callback-health-monitor). The 'operating boundary' text describes scope but not selection conditions or exclusions.

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