Probe an MCP endpoint and diff its tool schema against the last stored snapshot: tools added, removed, or whose description/inputSchema changed. Schema drift fails quietly mid-run, which is why it is worth checking.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL of the MCP endpoint to inspect. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses a notable behavioral trait—'Schema drift fails quietly mid-run'—and explains that the tool diffing reveals changes. However, it does not mention network prerequisites, potential latency, or return format, leaving some behavioral aspects uncovered, though enough is provided for a basic understanding.
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 sentences long, front-loaded with the core action ('Probe... diff...') and followed by a concise rationale. There is no redundant or filler text; every sentence adds value, earning a perfect score.
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 simple tool with one parameter and no output schema, the description covers the core functionality and even provides a motivating context ('why it is worth checking'). It does not explicitly describe the return structure or edge-case behavior, but given the low complexity, the description is largely adequate for an agent to select and invoke the tool 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?
The input schema already has 100% coverage for the single parameter 'url' with a clear description ('Public http(s) URL of the MCP endpoint to inspect'). The tool description adds no additional detail about the parameter, so the schema is the primary source of semantics; the baseline of 3 is appropriate for full schema coverage.
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 uses a specific verb ('Probe' and 'diff') and resource ('MCP endpoint tool schema against last stored snapshot'), clearly distinguishing it from generic checks. It enumerates the specific kinds of changes detected (tools added, removed, or description/inputSchema changed), making the purpose unambiguous and easily differentiated from sibling tools like check_mcp_endpoint.
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 provides clear context on when this tool is useful: for detecting schema drift that 'fails quietly mid-run', implying it should be used proactively when schema changes need to be caught. It does not explicitly name alternatives or exclusion cases, but the rationale for using the tool is well communicated.
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 distinct: get_known_tools and get_uptime read history, while check_mcp_endpoint is a general live probe. The only potential confusion is between check_mcp_endpoint and check_schema_drift, as both involve schema changes, but their descriptions clarify that one is a broad health check and the other is a focused diff.
All tool names follow a consistent verb_noun pattern: check_ for active probes and get_ for historical retrievals. This makes the tool's behavior predictable from its name.
Four tools is well-scoped for a validator/monitoring server, covering live checks and historical reads without unnecessary bloat.
The server covers live probing, schema drift detection, and historical views of tools and uptime. A minor gap is the lack of a tool to list all monitored endpoints or manage snapshots, but for the stated purpose the core operations are present.