A deliberately tiny, risk-free MCP server for learning how MCP directory listings work.
Repository: https://github.com/mikej345/hello-mcp
No network calls, no API keys, no user data. Every tool is read-only and pure. Runs over both MCP transports: stdio (for "runs from source" listings) and Streamable HTTP (for "hosted endpoint" listings).
Scored across 3 tools
add_numbers, get_rule_of_thumb, and get_server_time each cover a completely different operation: arithmetic, random advice, and time/health. There is no overlap or plausible way to confuse one tool with another.
All three tools follow a consistent snake_case verb_noun pattern: add_numbers, get_rule_of_thumb, get_server_time. The verbs clearly indicate the action and the nouns clearly identify the target, making the set predictable.
Three tools is a reasonable, small size for a demo-style server and avoids bloat. However, the operations are unrelated, so the set feels more arbitrary than intentionally curated.
There is no coherent domain or lifecycle against which to judge completeness; the tools are isolated, self-contained utilities. For a server named 'hello,' the lack of a greeting or hello-style operation is also a notable gap.
Add two numbers and return the sum.
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | The first number to add, e.g. 2 or -3.5. | |
| b | Yes | The second number to add, e.g. 3 or 10.25. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
It discloses a pure computation with no side effects, which is consistent with the annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false). It adds no extra behavioral context beyond those annotations, so the bar is met without being exceeded.
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?
A single, clear, front-loaded sentence with no wasted words. It communicates the operation and result immediately.
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 the simple pure-function nature, complete schema with 100% coverage, comprehensive annotations, and an output schema, the description is fully sufficient. No additional context is needed for an agent to call this 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?
Schema description coverage is 100% and both parameters already include detailed descriptions and examples. The tool description only repeats 'two numbers,' adding no meaningful semantics beyond the schema, so baseline 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 states a specific verb ('add'), the resource ('two numbers'), and the outcome ('return the sum'). It fully explains what the tool does and is clearly distinct from the unrelated sibling tools.
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 implies use whenever a sum of two numbers is needed, but it does not explicitly discuss when to use this tool versus alternatives or mention any exclusions. For a trivial arithmetic utility, the implied usage is adequate but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return one random engineering rule of thumb. Takes no input and has no side effects.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false)Skip, and the description adds that the tool is random and has no side effects, reinforcing the safe, read-only nature. It also clarifies the 'no input' constraint, which goes beyond the schema. No contradictions 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that delivers the core purpose and side-effect profile without any fluff. Both key facts are front-loaded and every word earns its place.
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 the zero-parameter schematok/contexts, an output schema exists, and sibling tools are unrelated, the description covers everything an agent needs. The tool's behavior is fully described by its randomness and lack of side effects.
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 tool has zero parameters alerting schema coverage is effectively 100%. The description explicitly states 'takes no input,' providing a clear semantic confirmation beyond the empty schema object. Per the rubric, a score of 4 is appropriate for no-parameter tools.
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 clear, specific verb and resource: 'Return one random engineering rule of thumb.' This fully differentiates it from sibling tools like add_numbers and get_server_time, which perform entirely different functions.
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 clearly conveys the contexts in which the tool is useful: when a random engineering heuristic is needed. It explicitly notes that no input is required and there are no side effects, but does not describe any exclusion criteria or alternative tools, though none are necessary given the distinct purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the server's current time in UTC (ISO 8601). Useful for checking the server is alive.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, and the description confirms read-only behavior ('Return'). It adds the return format (UTC ISO 8601), which is useful context. No side effects described, but none are implied by the tool's nature. The description is consistent 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise: one sentence stating the action and format, followed by a short usage hint. Information is front-loaded and every word earns its place. No fluff.
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 zero-parameter read-only tool with an output schema present (has_output_schema: true), the description is fully sufficient. It tells what the tool returns (UTC ISO 8601) and why to use it (aliveness check). Nothing missing for correct 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?
Tool has zero parameters, so the description need not explain any. The baseline for 0 params is 4, and the description does not add or need parameter details. Schema coverage is 100% (no params).
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 ('Return') and a precise resource ('server's current time in UTC (ISO 8601)'). Clearly distinct from siblings like add_numbers and get_rule_of_thumb, which have unrelated purposes. No ambiguity.
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?
Explicitly suggests a use case: 'Useful for checking the server is alive.' This gives clear context for when to call the tool. Does not discuss alternatives, but given the tool's simplicity and unrelated siblings, no exclusion is needed.
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.
add_numbersget_rule_of_thumbget_server_time
Add one secure layer between your agents and this server.