check_relay_health

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

No annotations are provided, so the description carries the full behavioral burden. It does list what is inspected and even what stuck-transaction output includes (txid, nonce, pending duration), which is useful, but it never explicitly states that the tool is read-only and side-effect-free, nor does it mention permissions or rate limits. The implications of 'check' and 'diagnostics' are reasonably strong, but for a tool with zero annotation coverage an explicit safety profile would be expected.

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 description is front-loaded with purpose and scope, and the bullet list is efficient. The final tip to call `earning_opportunities` is unrelated to relay diagnostics and is the one sentence that does not earn its place, but it does not undermine the overall structure.

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?

Given there is no output schema, the description usefully enumerates what is checked and what stuck-transaction output contains, which is the main thing an agent needs. It also clarifies the relationship to x402 payment states. The main omission is a clear statement that the operation is read-only and non-destructive, which matters because there are no annotations to convey that.

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 zero parameters, so the baseline is 4. The description correctly implies no caller-supplied arguments are needed, and there are no schema gaps to compensate for.

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 with a specific verb and resource: 'Check the sponsor relay health and nonce status,' and the bullet list makes the scope concrete (availability, nonce gaps, mempool desync, stuck transactions). It distinguishes itself from payment lifecycle polling, but does not name overlapping siblings like nonce_health or nonce_fill_gap, which also sound like nonce diagnostics.

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 explicitly frames the tool as 'operator diagnostics around relay-owned sponsor state' and warns that paymentId polling is the source of truth for payment lifecycle, so the agent knows one clear non-use case. However, it gives no guidance relative to the many overlapping nonce tools (nonce_health, nonce_fill_gap, nonce_heal, recover_sponsor_nonce), leaving the agent without a rule for when to choose this tool versus those.

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