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

Beyond the annotations (readOnly, idempotent, openWorld), the description discloses the upstream data source (mempool.space public API), the data freshness implied by tiered estimates, and — critically — the quota and payment model: 10 free calls/day then $0.001/call via x402 (_meta["x402/payment"]) or an X-API-Key. That is exactly the auth/rate-limit context an agent needs to avoid unplanned spend.

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 return-value clause is front-loaded and dense with useful specifics, but the sentence is long and mixes purpose, billing mechanics, and a vendor tag. The trailing "[served by tools.moneytools.dev]" is noise that consumes attention without helping invocation.

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 one-parameter, no-required-arg tool with an output schema and full read-only annotations, the description covers source of truth, quota, payment paths, and default sizing — enough to call it correctly. Only explicit selection guidance against sibling tools is absent, which is a minor gap given the tool's narrow, self-evident scope.

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 coverage is 100% and the single vbytes parameter already documents its meaning and the 141 default, so the schema carries the load. The description only indirectly signals that the caller's transaction size drives the sats/USD cost output; it adds no unit or format detail beyond the schema. Baseline 3 applies.

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?

"Recommended sat/vB for next block, 30 min, 1 hour and economy" names the exact resource, the four fee tiers returned, and the derived fiat/sats cost output. An agent can tell immediately this is a read-only fee oracle distinct from address or chain tools like btc_address or chain_info.

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?

Usage is only implied: the returned fields make it obvious you call this to price a transaction, and the vbytes default hints at fee estimation for a planned tx. There is no explicit when-to-use versus alternative guidance, no when-not-to-use, and no mention of when the paid tiers become relevant to the decision.

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