Server Quality Checklist

Tool Scores

• analyzeB
  3.4/5.0
  Behavior2/5

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

  No annotations provided. Description implies read-only ('analyzes'), but does not explicitly state non-destructiveness, performance impact, or any side effects.

  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, concise and front-loaded with the main action and outputs. No fluff.

  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?

  No output schema, but description describes return fields (severity, description, suggestions). Missing details about how comparison works given afterPath/beforePath, especially compared to sibling compare_snapshots.

  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%, so baseline 3. Description adds context about 'built-in rules' and return format, but does not explain the comparison parameters (afterPath, beforePath) beyond what schema 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?

  Clearly states it 'Analyzes a memory snapshot' and lists specific detections (leaks, fragmentation, etc.). Distinguishes from sibling tools like list_processes, snapshot, compare_snapshots.

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

  Usage Guidelines2/5

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

  No guidance on when to use this tool vs siblings (e.g., compare_snapshots). Does not specify prerequisites or when not to use.

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

• list_processesA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It discloses that the tool excludes certain process types and that discovery is via IPC endpoints, which is useful. However, it doesn't mention whether the operation is read-only, whether it requires elevated permissions, or what happens if no processes are found. The exclusions are a behavioral trait, but more context (e.g., performance implications, side effects) would be helpful.

  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 with no waste. The core purpose is front-loaded, and the exclusion detail is concise. Every word earns its place.

  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?

  For a list tool with one optional parameter and no output schema, the description is largely complete. It explains what is listed, how they are discovered, and what is excluded. The only minor gap is not describing the return format (e.g., whether it returns process names, IDs, or full details), but since there's no output schema, a brief note on return shape would improve completeness. Still, the description is adequate for an agent to call it correctly.

  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%, so the schema already documents the filter parameter. The description adds context about what the filter matches (process name) but doesn't add syntax or format details beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting.

  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 lists running .NET processes suitable for memory profiling, discovered via diagnostic IPC endpoints. It also specifies exclusions (IDE, tooling, MCP server processes), which distinguishes it from generic process-listing tools and provides concrete scope.

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

  Usage Guidelines3/5

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

  The description implies when to use it (when you need to identify .NET processes for memory profiling) and what it excludes, but it does not explicitly mention alternatives or when not to use it. Sibling tools like snapshot, analyze, and compare_snapshots suggest a workflow, but the description doesn't route the agent to them or explain how list_processes fits into that workflow.

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

• compare_snapshotsA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden and it does disclose key behavior: two snapshots, delay, and return of IDs/paths. However, it does not discuss side effects, possible failures, blocking behavior, or whether the tool is purely read-only, leaving room for unanticipated runtime behavior.

  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 short, purposeful sentences. The action is front-loaded, the use case is given immediately after, and the required input plus return are stated clearly with no filler.

  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?

  The description covers what the tool does, why to use it, an important input requirement, and what it returns. Since the schema already documents the remaining parameter details, this is sufficiently complete for a tool with these siblings, though it does not explain its relation to a single snapshot tool.

  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% for all 4 parameters, so the baseline is 3. The description adds value by clarifying that pid is effectively required despite being nullable/optional in the schema, and says 'with a delay between them' which aligns with delaySeconds and reinforces its role.

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

  Purpose4/5

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

  The description states a specific action: 'Takes two memory snapshots of a .NET process with a delay between them' and explicitly connects this to memory-leak detection. It is distinguishable from the sibling 'snapshot' tool by the two-snapshot nature, though it does not name alternatives directly.

  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?

  It gives clear context: detecting memory leaks by comparing before/after state, and it tells the agent that a pid must be provided. It does not explicitly mention when not to use this tool or name a sibling alternative, so exclusions are missing.

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

• get_rulesA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It indicates read-only behavior and specifies the configuration file location, but lacks details on edge cases (e.g., empty list, error states).

  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 consists of two focused sentences, the first stating the tool's purpose and the second providing configuration context. Every sentence is essential and there is no redundancy.

  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?

  For a parameterless list tool with no output schema, the description is comprehensive: it specifies the output fields and the source of rules. Minor improvement could be noting that the list reflects current active configuration.

  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?

  Since there are zero parameters (baseline 4), the description adds value by explaining the output fields and the configuration file location, which is not evident from the empty input schema.

  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 the verb 'Lists' and specifies the resource 'active analysis rules', clearly communicating the tool's function. It also mentions the output fields (ID, title, severity, category), making it distinct from sibling tools like list_processes or snapshot.

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

  Usage Guidelines3/5

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

  The description implies usage when one needs to see available analysis rules, but does not provide explicit guidance on when to use this tool versus alternatives or when not to use it.

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

• snapshotA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral burden. It states what the tool does, that the target must be running, and what it returns, but it does not disclose side effects, required permissions, or behavior on invalid pids. This is adequate but not deeply transparent.

  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 short, focused sentences with no filler. The action, the required input, and the return value are each clearly stated and naturally ordered. Every sentence earns its place.

  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?

  The description says what the tool does, what input it truly requires, and what it returns next for usage. The non-pid parameters are already fully documented in the simple schema, and the usage is a running output is a next-step hint. It is enough for a simple snapshot/analyze workflow.

  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?

  The schema already gives 100% parameter coverage, so the baseline is 3. The description adds meaningful value by making clear that a pid must be provided, even though the pid schema field is marked nullable. This helps the agent avoid relying on the null default.

  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 names a specific verb action ('Takes a memory snapshot') and a specific subject ('a running .NET process'), and it explains that the result is 'a snapshot id to pass to analyze.' This clearly positions it against sibling tools like list_processes and compare_snapshots.

  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 usage context is clear: when a .NET process snapshot is needed, provide a pid and receive a snapshot id for later analysis. It doesn't explicitly name alternatives or exclusions, but the workflow and prerequisites are unambiguous enough for an agent to invoke correctly.

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