Skip to main content
Glama

MCPFax Reliability

by com.mcpscores

Integration drift

mcpfax_integration_drift
Read-onlyIdempotent

What changed under an x402 endpoint or MCP server you have ALREADY integrated: payTo rotations, price, asset and network changes, terms added or removed, and tool-schema changes. This is not a discovery tool and will not help you choose a server; it tells you whether the one you wired in still matches what you wired in. Pass up to 50 subjects and the since watermark returned by your last call, and you receive only what changed after it plus a fresh watermark, so repeat checks stay cheap. A subject with no changes is reported as verified-unchanged with the date that is true as of — that is a real answer and is billed. A subject MCPFax has never observed is named in not_observed and given NO verdict, because reporting "no changes" about something we never watched is indistinguishable from a genuine all-clear. The watermark is the last date MCPFax actually observed, never the current clock, so no window is skipped between sweeps. Coverage is young and every response carries its archive span. Costs $0.002 USDC per call via x402 on Base.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sinceNoThe watermark from your previous call (YYYY-MM-DD). Omit on a first call to receive the whole archive.
subjectsYesComma-separated endpoint URLs or host identifiers to check, at most 50, e.g. 'https://x402.browserbase.com/browser/session/create,host:api.example.com'.

TDQS

A4.9/5.0
Behavior5/5

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

Adds significant behavioral details beyond the readOnlyHint/idempotentHint annotations: billing per call, watermark semantics (last observed date, not current clock), the not_observed behavior with no verdict, verified-unchanged as a real billed answer, and archive span caveat. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every sentence carries information. It is front-loaded with purpose, then usage, then behavioral caveats. Slightly long, but no waste; could arguably be split into two paragraphs for readability, but the content justifies the length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description explains what is returned (changes after `since` plus fresh watermark, verified-unchanged with date, not_observed list). It covers cost, coverage span, and uses clear examples. For the tool's complexity, this is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds crucial meaning: explains `since` is the watermark from the previous call and can be omitted on first call, clarifies subjects is a comma-separated list (max 50), and clarifies the semantics of the watermark (last observed date). This goes well beyond the schema's field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: it tells you 'what changed under an x402 endpoint or MCP server you have ALREADY integrated' and enumerates concrete change types (payTo rotations, price, asset, network, terms, tool-schema). It explicitly distinguishes from siblings by stating it is not a discovery tool and will not help choose a server.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: to check whether an already-integrated server still matches. Explicitly names an alternative use ('This is not a discovery tool') and gives operational guidance (pass up to 50 subjects, use the `since` watermark from the last call).

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

All MCPFax Reliability toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation5/5

Each tool targets a distinct aspect: endpoint risk, revenue, integration drift, payer profile, change feed, preflight, and wallet authenticity. The descriptions explicitly differentiate them, even when two tools involve wallets or risk, making misselection unlikely.

Naming Consistency5/5

All tool names follow the same mcpfax_ prefix followed by a descriptive compound noun (endpoint_credit_score, integration_drift, payto_change_feed). The pattern is uniform and predictable, differing only in the domain-specific phrase.

Tool Count5/5

Seven tools is within the ideal 3-15 range and well-scoped for a reliability-focused MCP server. Each tool covers a necessary function without redundancy, from pre-flight checks to ongoing drift monitoring.

Completeness5/5

The server covers the full lifecycle of managing reliability: pre-integration vetting (credit, revenue, wallet checks), post-integration monitoring (drift, change feed), and pre-call verification (preflight). The feed and drift tools handle ongoing awareness, leaving no obvious dead ends.

Resources