Server Quality Checklist

Tool Scores

• token.provisionA
  3.9/5.0
  Behavior1/5

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

  Description states starting a free device trial, which is a side effect, but the annotation declares readOnlyHint=true. This contradiction misleads about whether the tool modifies state. Per rubric, contradiction yields score 1.

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

  Conciseness5/5

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

  The description is a single sentence that packs all essential information: purpose, duration, fallback, and return value. It is front-loaded and concise, with no wasted words.

  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?

  For a simple tool with one optional parameter and no output schema, the description covers the return value (token_prefix and expiry), explains authentication, and notes the 12-hour validity. It is complete for the agent to use the tool correctly.

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

  Parameters4/5

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

  Schema coverage is 100% with a clear description for the refresh parameter. The description adds context about the environment variable fallback, which helps understand when refresh might be useful, beyond what the schema alone provides.

  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?

  Description clearly states the tool obtains a 12-hour ngsrv agent token for tunnel commands. It specifies the verb, resource, duration, and purpose. It is well-distinguished from sibling tools like tunnel.list or tunnel.start.

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

  Usage Guidelines4/5

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

  Description explains when to use this tool (for tunnel commands) and describes fallback behavior (uses environment variable or starts free trial). However, it does not explicitly state when not to use or mention alternatives, but given sibling tools are different, the context is sufficient.

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

• tunnel.startA
  4/5.0
  Behavior3/5

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

  Annotations indicate openWorldHint=true, and the description confirms side effects by exposing a server. It adds that the tool uses ngsrv and returns values, but does not disclose prerequisites (e.g., needing a token) or potential limitations like tunnel duration.

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

  Conciseness5/5

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

  The description is three concise sentences, front-loading the core action and output, followed by use cases and a follow-up suggestion. No wasted words.

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

  Completeness4/5

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

  Given the simple single-parameter tool and annotations, the description is reasonably complete: it covers the action, output, and use cases. It lacks error handling or prerequisites but is sufficient for basic operation.

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

  Parameters3/5

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

  Schema coverage is 100% with a detailed description and examples for the port parameter. The tool description does not add additional meaning beyond the schema, so it meets the baseline for high coverage.

  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 clearly states the tool exposes a local HTTP server on a public URL via ngsrv and returns specific fields. It distinguishes from sibling tools like tunnel.list and tunnel.stop by mentioning use cases and suggesting a follow-up.

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

  Usage Guidelines4/5

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

  The description provides explicit use cases (webhooks, OAuth callbacks, sharing dev servers) and suggests using tunnel.list afterward, giving clear context. However, it does not explicitly state when not to use this tool.

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

• tunnel.listA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds value by specifying the scope ('current session'), return fields, and its role as a precursor to tunnel.stop, without contradicting annotations.

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

  Conciseness5/5

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

  The description is two sentences, front-loaded with the action and key details. Every sentence is useful, with no redundancy or filler.

  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?

  For a simple list tool with one optional parameter and no output schema, the description adequately explains the return fields, session scope, and relationship to sibling tools (tunnel.stop). No gaps remain for an agent to successfully use it.

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

  Parameters3/5

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

  The input schema has 100% description coverage with a clear description for the optional 'limit' parameter. The description does not add extra meaning beyond what the schema provides, so a baseline 3 is appropriate.

  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 explicitly states 'List HTTPS tunnels started by this MCP process in the current session' and specifies return fields (port, public_url, started_at). This clearly distinguishes it from sibling tools like tunnel.start and tunnel.stop.

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

  Usage Guidelines4/5

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

  The description advises 'Call this before tunnel.stop to confirm which port to close,' providing explicit usage context. While it doesn't cover all alternatives, it gives a concrete use case that helps an agent decide when to invoke this tool.

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

• docs.installA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate read-only, non-destructive, idempotent. The description adds that the tool returns static text (commands/snippets) and does not start a tunnel, which is valuable beyond the annotations. No contradictions.

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

  Conciseness5/5

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

  Three focused sentences: purpose, trigger conditions, and a negative constraint. No filler words; front-loaded with the core action. Every sentence earns its place.

  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?

  For a simple, single-parameter, read-only documentation tool with no output schema, the description fully covers when to use, what it returns, and what it avoids. No gaps detected.

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

  Parameters3/5

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

  Schema description coverage is 100% for the single parameter, with a clear description and examples. The description adds no extra 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.

  Purpose5/5

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

  The description clearly states it returns 'ngsrv CLI install commands and MCP client configuration snippets', specifies trigger phrases ('install ngsrv, configure Cursor, or use npx'), and distinguishes from siblings by noting it does not start a tunnel.

  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 call ('when the user asks how to install ngsrv...') and provides an exclusion ('Does not start a tunnel'), guiding the agent to alternative tools like tunnel.start. No ambiguity about context.

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

• tunnel.stopA
  4.7/5.0
  Behavior4/5

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

  Annotations indicate destructiveHint and idempotentHint. Description adds that it only stops tunnels started by this session and emphasizes correct port usage. Minor gap: no details on behavior if tunnel doesn't exist.

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

  Conciseness5/5

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

  Two sentences, no unnecessary words, front-loaded with purpose and immediate action guidance.

  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?

  For a simple tool with one required parameter and no output schema, the description is complete: covers what, how, and when to use, with sibling guidance.

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

  Parameters4/5

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

  Schema covers parameter fully. Description adds context that port must match from tunnel.start and suggests verification via tunnel.list, beyond schema's type and range.

  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 clearly states it stops a tunnel started by the MCP session, using the verb 'stop' and specifying the resource 'ngsrv tunnel'. It distinguishes from siblings like tunnel.start and tunnel.list.

  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?

  Provides explicit guidance to pass the same port from tunnel.start and suggests calling tunnel.list first if unsure, offering a clear alternative and prerequisite.

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