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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, and the description still adds substantial behavior: no network request, fetch, money movement, message, sharing, config change or external write; the x402 pricing at 0.10 USDC per call on Base with 10 free signed-wallet calls per rolling 30 days; the X-Wever-Wallet-Proof binding to the exact JSON arguments and route; and the Ed25519 signed receipt. Cost, auth mechanics, and side-effect boundaries are exactly the context annotations cannot convey.

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 definition is a small number of extremely long, clause-stacked sentences that are hard to parse, with heavy noun-phrase chaining ('names a system that restarts, keeps no record, keeps one an interruption wipes or does not name what is done'). The front-loaded opening is reasonable, but the middle is not scannable and the verdict enumeration is embedded rather than structured. It is over-dense rather than over-long.

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 6-parameter tool with nested objects and no output schema, the description covers the verdict space, the signed-receipt return, the read-only guarantee, pricing/auth, and pointers to the contract and human page. The only shortfall is that it does not explain how missing optional parameters (record, system, on_interruption, interruptions) affect the verdict, leaving the agent to infer default behavior.

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 83%, so the baseline is 3, but the description goes further by explaining how the parameters relate: per-step ordering with whether finishing writes a record a resumed run reads and what rerunning costs, the four-way record location (durable store, process, agent context, nowhere), whether done/remaining steps and outputs are named, and interruptions with the stopping step and the step the next run picked up from. This mirrors and contextualizes the nested fields rather than merely repeating them.

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 definition names a specific resource (a task system's resume behavior: steps, record location, interruption handling) and a concrete output (a signed report with a verdict among work_restarts, resume_gaps, resume_unverified, resumes_from_record). It explicitly differentiates itself from three siblings by naming their distinct scopes. The core verb is buried in a dense run-on clause ('Agent Recovery: submit a task system: ...'), which keeps it from being a clean 5.

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?

It routes the agent away from adjacent tools with concrete conditions: a half-finished job assembled into a resume pack goes to wever_job-handoff-pack, backup/restore data steps go to wever_recovery-readiness-check, and a post-payment missing result goes to wever_payment-recovery-check. That is explicit alternative guidance. It does not state a clear 'do not use this when' beyond those routing notes, so it stops short of 5.

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