Haveno peer-to-peer quotes against centralized spot over time, both sides.
window in 24h,7d,30d,90d,1y. History starts on 24 August 2026, when recording began.
| Name | Required | Description | Default |
|---|---|---|---|
| window | No | 7d |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does add a key behavioral constraint by stating history starts on 24 August 2026. It also notes that 'both sides' are included, which clarifies the data scope. It does not mention response format, update cadence, or side effects, but for a read-only quote query the most important constraints are disclosed.
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 two terse sentences with no filler. The first sentence establishes the comparison and scope, and the second sentence specifies parameter options and the data-recording constraint. Every clause contributes essential information.
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 a single optional parameter and no output schema, the description covers the tool's core purpose, the accepted window values, and a key temporal limitation. It leaves the exact output structure and the precise meaning of 'both sides' to inference, but these are unlikely to prevent correct selection and invocation.
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 input schema only lists a single 'window' string with no enum or description, so schema coverage is 0%. The description fully compensates by enumerating the accepted values: '24h,7d,30d,90d,1y' and adding the recording start date, giving an agent everything needed to choose a valid value.
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 identifies a distinct resource: Haveno peer-to-peer quotes compared against centralized spot, explicitly covering both sides and a time dimension. It does not use a crisp verb phrase like 'list' or 'retrieve,' but the scope is specific enough to separate it from sibling tools such as price or haveno_book.
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 phrase 'over time' and the provision of window options imply this tool is for historical time-series queries rather than one-off current prices or order book data. However, it never explicitly names alternatives or states when not to use this tool, leaving the routing decision mostly to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly grouped by prefix (network_, pool_, haveno_, reorg), but there is overlap: get_block vs search_block both return block details, price vs haveno_book both expose the current Haveno order book, and chain_fork_window, recent_orphans, and reorgs all touch chain-fork/orphan phenomena. The descriptions help separate them, but an agent could easily pick the wrong one.
The dominant convention is a domain_noun pattern (network_hashrate, pool_distribution, haveno_premium, chain_provenance), which is predictable and readable. Minor deviations like get_block, search_block, price, and reorgs break the pattern slightly, but not enough to cause confusion.
18 tools is on the heavier side but reasonable for a metrics/analytics server covering network health, mining pools, reorgs, blocks, and Haveno market data. A few endpoints could potentially be consolidated, but each tool generally earns its place.
The surface covers current network state, historical time series, block lookup, orphan/reorg analysis, pool attribution, and Haveno market data, which is solid for a Monero metrics server. Minor gaps like transaction-level lookup or a direct chain-range endpoint are absent, but agents can work around them using the provided block and fork-window tools.