Independent health, price and history for x402/MPP endpoints. Metered over x402; free grade on web.
Scored across 2 tools
Both tools have nearly identical descriptions, differing only by a final sentence in the grade tool. An agent would likely struggle to choose between them, as they appear to serve the same purpose of probing endpoint status and history.
Both tool names follow the same pattern: 'probe402_endpoint_' followed by a distinct noun ('grade' vs 'history'). This is a clear, consistent naming convention.
With only two tools, the server feels thin for even a niche service. While a focused probe tool could reasonably have a small surface, two tools is borderline and may leave users wanting more.
The tool set is missing clear separate functionality—the history tool's description is almost identical to the grade tool, leaving ambiguity about what each actually does. There are no additional operations like comparing endpoints or configuring probes, so the surface seems incomplete for a full observatory service.
The Machine Commerce Observatory: independent readings of x402 and MPP endpoints — alive right now, quoting what, and how fast? Probed on a fixed clock under one published rubric, every reading traceable to a retained capture. Blocked and rate-limited are told apart from unreachable at capture time, so a defended endpoint is never reported as dead. Call before paying an unfamiliar endpoint, or to check whether one you use has repriced or rotated its payTo. This tool is the FREE grade: current observation plus 7 days of counts. The same record our published reports are written from.
| Name | Required | Description | Default |
|---|---|---|---|
| endpoint_id | Yes | probe402 endpoint id, from the free /coverage list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses key behavioral details: endpoints are probed on a fixed clock, blocked/rate-limited are distinguished from unreachable, and readings are traceable to retained captures. It also mentions the output includes current observation plus 7 days of counts, but does not detail exact response format or any side effects.
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 somewhat verbose with marketing-like phrasing, but it front-loads the purpose and includes all essential details. It is not overly long and every sentence contributes useful context, though it could be tightened without losing meaning.
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 tool with one parameter and no output schema, the description covers the purpose, when to use it, and key behavioral aspects. It explains what the tool returns (current observation plus 7 days of counts) and mentions the methodology. It lacks explicit response structure details, but given the simplicity, it is sufficiently complete.
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 single parameter endpoint_id has 100% schema description coverage, so the schema already explains it. The description does not add extra meaning about the parameter beyond what the schema provides, so the baseline score of 3 is appropriate.
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 clearly states the tool's function: providing current readings of x402 and MPP endpoints, including aliveness, quoting, and speed. It also differentiates from the sibling tool by specifying this is the 'FREE grade' with current observation plus 7 days of counts, making it distinct from the history tool.
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 description explicitly advises calling this tool before paying an unfamiliar endpoint or checking for repricing/rotation of payTo. It implies the sibling is for history, but does not explicitly name the alternative or state when not to use it. The guidance is clear and actionable, though not exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The Machine Commerce Observatory: independent readings of x402 and MPP endpoints — alive right now, quoting what, and how fast? Probed on a fixed clock under one published rubric, every reading traceable to a retained capture. Blocked and rate-limited are told apart from unreachable at capture time, so a defended endpoint is never reported as dead. Call before paying an unfamiliar endpoint, or to check whether one you use has repriced or rotated its payTo.
| Name | Required | Description | Default |
|---|---|---|---|
| endpoint_id | Yes | probe402 endpoint id, from the free /coverage list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even though readOnlyHint already communicates read-only behavior, the description adds useful behavioral nuance: probes occur on a fixed clock, every reading is tied to a retained capture, and blocked/rate-limited endpoints are distinguished from unreachable ones at capture time, so defended endpoints are never reported as dead. This is property information an agent cannot infer from the annotations alone.
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 first sentence front-loads the purpose and the later sentences add meaningful contextual guidance, but the language is deliberately embellished ('Machine Commerce Observatory', 'alive right now, quoting what, and how fast?'). Every sentence earns its place topically, yet the style is more promotional than a plain description would require for a one-parameter read-only tool.
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 single-parameter, read-only history lookup, the description covers what the data includes (liveness, quote, speed), how it is collected (fixed clock, retained captures), and what the classification means (blocked vs unreachable). The output shape is not specified, but with no output schema and a simple fetch-by-id operation, the provided context is sufficient for an agent to call it correctly.
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 lone parameter, endpoint_id, is already documented as 'probe402 endpoint id, from the free /coverage list'. The description only refers to the endpoint in prose and does not add new format, source, or fallback semantics, so it meets the baseline without exceeding it.
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 states a specific capability: it returns independent historical readings of x402 and MPP endpoints, with liveness, quote, and response speed, all traceable to a retained capture. This goes beyond a generic 'get history' and distinguishes the tool from its sibling probe402_endpoint_grade, which is a grade rather than a temporal record. An agent can tell what this tool is for without opening the schema.
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 description gives concrete usage triggers: call before paying an unfamiliar endpoint and to check whether a known endpoint has repriced or rotated its payTo. It does not explicitly name the alternative probe402_endpoint_grade or state when to prefer that sibling, so it misses a crisp exclusions, but the when-to-use guidance is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
probe402_endpoint_gradeprobe402_endpoint_historyLive x402 endpoint trust/diligence check before you pay it. $0.02/call via x402.
Free, read-only MCP subset of x402 Toolbox's cheap data endpoints, free via MCP.
Check what a paid x402 endpoint or MCP server delivered, from probes anyone can repeat.
Independent uptime oracle for the x402 agent economy. Free probes, paid history via USDC on Base.
Add one secure layer between your agents and this server.