Run a controlled synthetic health check and store its result. NOT an external service probe.
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"scenario": "<scenario>"
},
"name": "check_demo"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| scenario | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses that a result is persisted (a write side effect) and that no external network call occurs, which is more than nothing. It omits whether the run is idempotent, whether repeated calls overwrite prior results, what error/permission conditions exist, and what the stored result contains.
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?
Two short sentences, front-loaded with the action and immediately followed by the disambiguating exclusion. No filler, no restatement of the title.
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 tool with no output schema, the description covers purpose and one safety-relevant fact (no external probe, result stored). It is still incomplete on the point that matters most: the meaning and expected outcome of each scenario enum value, plus where/how the result is stored.
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 has an enum of 'healthy', 'malformed', 'unavailable' with 0% schema description coverage, so the description is the only place semantics could be explained. It says nothing about what each scenario simulates — critically, whether 'unavailable' or 'malformed' intentionally produce a failure/error response rather than a successful check. That ambiguity can lead an agent to misread a deliberate failure as a tool malfunction.
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?
States a specific verb and resource ('Run a controlled synthetic health check and store its result') and adds an explicit negative scope ('NOT an external service probe') that separates it from the sibling check_live. It stops just short of naming the sibling outright, so the differentiation is inferential rather than stated.
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 negation 'NOT an external service probe' implicitly tells the agent when not to use this tool, which is real guidance. However, it never states the positive condition ('use this to validate the synthetic/demo pipeline') and never names check_live as the alternative for real probes, leaving the agent to infer routing from sibling names.
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.