Server Quality Checklist

Tool Scores

• debug_continueA
  4.2/5.0
  Behavior4/5

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

  Annotations already disclose destructive, non-read-only, non-idempotent behavior. The description adds valuable context by warning that resuming 'changes debuggee execution state and may allow the target to perform normal application side effects before the next stop.' No contradiction 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.

  Conciseness5/5

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

  Three sentences, front-loaded with the core action, followed by usage constraints and a side-effect warning. Every sentence contributes meaning; there is no filler or 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 mutation-style debugger tool with no output schema, the description covers scope, invocation timing, exclusions, and side effects. It does not explicitly describe the call's return value, but the waitForStop parameter already conveys the relevant stopping behavior.

  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 all three parameters are already documented. The description adds little beyond reinforcing that threadId refers to a paused thread, which is already in the 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 states a specific verb and resource: 'Resume one paused thread in a live debug session.' It clearly distinguishes this from postmortem/crash-dump tools by explicitly excluding those targets.

  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 explicit when-to-use guidance: 'after inspecting a stopped state when execution should proceed to the next stop or termination.' It also gives an explicit when-not-to-use condition for crash dumps, but it does not name the alternative sibling tool for postmortem analysis.

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

• debug_this_crashA
  4.4/5.0
  Behavior5/5

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

  Annotations mark the tool destructiveHint=true and readOnlyHint=false, and the description expands that into concrete guidance by warning that execution modes 'can run application code and cause its normal side effects.' It further distinguishes current/dump as 'only inspect stopped evidence' and discloses deterministic fixed/blocked/budget-exhausted outcomes, which annotations do not convey.

  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 sentences with clear roles: mode overview, safety boundary, and workflow/return summary. It is dense but every sentence earns its place, and the front-loaded 'Preferred high-level native crash workflow' gives immediate orientation for a complex 18-parameter tool.

  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 tool with 18 parameters, nested objects, and no output schema, the description covers the high-level decision axes of mode, safety, and workflow.stage, and what to expect in return. It leaves detailed response shape and substage mechanics to the schema or runtime, which is a modest gap given the schema's own richness.

  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 schema has 100% description coverage, so the baseline is 3, and the description mostly restates mode and workflow.stage semantics already present in the schema. It adds limited selection-level framing, such as read-only postmortem versus execution-capable modes, but it does not materially expand parameter meaning beyond the well-described fields.

  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 is explicitly framed as the 'Preferred high-level native crash workflow' and enumerates five modes, making it clear the tool owns end-to-end crash debugging rather than a single snapshot or disconnect action. It does not explicitly say how it differs from sibling tools like debug_diagnose_stop or debug_open_dump, so the differentiation is implicit through 'preferred high-level' and the mode 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?

  Mode-to-condition mapping is explicit: current for an already stopped session, dump for read-only postmortem analysis, codelldb/lldb-dap to discover and launch local binaries, live for an initialized DAP adapter. It also provides a clear exclusion: do not use codelldb/lldb-dap/live when execution/attach is unauthorized, since those modes run code while current/dump only inspect stopped evidence. workflow.stage is also mapped to diagnose/verify/autonomous.

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

• debug_diagnose_stopA
  4.7/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint and idempotentHint, and the description reinforces this with 'read-only' and 'without changing execution state.' It adds value by disclosing the return contract—bounded snapshot plus derived diagnosis—and that collection limitations are reported when optional debugger evidence is missing.

  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 carry the full purpose, scoping condition, alternative, and return contract. Information is front-loaded and every clause 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 10-parameter tool with no output schema, the description covers what the tool does, when to use it, what it returns, and how it behaves under missing evidence. Combined with exhaustive schema descriptions and safety annotations, little is left for an agent to infer.

  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%, and all ten parameters have descriptive schema text, so the description does not need to repeat them. It adds high-level context like project-frame selection and bounded evidence, but no parameter-level detail, so the 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 opens with a specific verb and resource: diagnosing an already stopped live or postmortem debug session, and explicitly says it does so without changing execution state. It lists the diagnostic outputs and distinguishes itself from debug_snapshot, so an agent can tell it apart from siblings.

  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?

  It gives an explicit condition: use this when the debugger has captured the failure and you need derived diagnosis; use debug_snapshot when only raw evidence is needed. This names the alternative and the deciding factor, which fully satisfies the dimension.

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

• debug_disconnectA
  4.7/5.0
  Behavior5/5

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

  The annotations already declare destructiveHint=true, but the description goes well beyond that by explaining that the adapter process is stopped, that terminateDebuggee=true may kill a live target, that the operation destroys current runtime state, and that it cannot be treated as read-only. This is rich, specific behavioral context.

  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 sentences, each earning its place: the core function, the usage timing, and the destructive caveat. The information is front-loaded and there is no filler or redundancy.

  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 tool with one optional parameter, no output schema, and strong destructive annotations, the description covers everything needed for correct invocation: what it does, when to use it, when not to use it, and what side effects to expect. Nothing essential is missing.

  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% and the schema already fully explains terminateDebuggee's true/false behavior. The description adds a cautionary note about state destruction, but this mostly reinforces the schema rather than adding new parameter-level meaning. 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 opens with a specific, concrete action—'End the active DAP session and stop its local adapter process'—making the tool's purpose unmistakable. It clearly differentiates this from sibling tools that run, continue, or diagnose, because it is a terminal cleanup operation rather than a debug-stepping action.

  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?

  The description gives an explicit use case ('when debugging is finished or the session must be reset') and an explicit negative case ('do not call it when more runtime evidence is still needed'). Although it doesn't name an alternative tool, the condition is unambiguous and the sibling list supplies the obvious alternatives.

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

• debug_open_dumpA
  4.7/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, and the description adds valuable specifics: it starts only the local debugger adapter, never launches or resumes the crashed program, treats the dump as read-only, and returns the initial stack/locals/registers plus optional modules and disassembly. This goes beyond the annotations and directly supports safe invocation.

  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 sentences with no filler. It front-loads the core action, then provides usage guidance, then summarizes behavioral guarantees and return contents. Every sentence contributes distinct value.

  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?

  Despite having 13 parameters and no output schema, the description provides enough context for correct selection and invocation: when to use it, what it does and does not execute, and what evidence it returns. The remaining parameter details are fully covered by the schema, so nothing critical is missing.

  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 baseline is 3. The top-level description does not add per-parameter meaning beyond the schema, though it does reinforce high-level intent such as optional modules and disassembly. Since the schema already documents each parameter well, the description's contribution here is adequate but not exceptional.

  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 a specific verb ('Open') and resource ('local native core/minidump'), and immediately distinguishes this from live-debugging siblings by noting it is for already-recorded failures with no target process execution. It also names the two supported adapters and the postmortem evidence captured, leaving no ambiguity about what the tool does.

  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?

  The description explicitly says when to use the tool ('when the failure is already recorded and no target process should execute') and names the alternatives for live reproduction ('use debug_run_to_stop or debug_this_crash instead'). This gives an agent clear routing guidance with no inference required.

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

• debug_run_to_stopA
  4.7/5.0
  Behavior5/5

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

  The description explains the meaningful behavioral side effects beyond the annotations: launch mode executes application code, attach mode changes debugger control of an existing process, and normal target side effects may occur before stopping. This aligns with destructiveHint=true and openWorldHint=true while adding practical context about what changes on the target.

  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 dense but every sentence earns its place: core behavior, usage boundaries, side-effect warning, and return summary. Key limitations are front-loaded, and there is no filler or repetition of the tool name.

  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?

  Despite having no output schema, the description clearly states what is returned: request result, terminal/stopped outcome, session status, and a bounded snapshot only on a stopped event. It also covers prerequisites, side effects, and forbidden usage contexts, which is sufficient for an agent to invoke and interpret the tool 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 structured schema already documents every parameter. The description adds a high-level note that the snapshot is bounded and only captured on a stopped event, which reinforces the schema, but it does not add substantial semantic meaning beyond what the parameter descriptions already provide.

  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 and resource: running one live launch or attach through an initialized DAP adapter until a terminal event. It also distinguishes the tool from postmortem workflows, so an agent can understand scope and avoid confusing it with dump or diagnostic tools.

  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?

  It explicitly says when to use the tool ('when you need deterministic runtime evidence from a reproduction') and when not to use it ('do not use it for a postmortem dump or when executing/attaching to the local target is not authorized'). This provides clear selection guidance without needing to infer from sibling names.

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

• debug_snapshotA
  4.7/5.0
  Behavior5/5

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

  Annotations already mark the tool read-only, idempotent, and non-destructive. The description adds valuable behavioral context beyond annotations: the snapshot does not resume execution, is best-effort, and may include collection errors when an adapter cannot provide optional data. This is exactly the kind of operational nuance an agent needs.

  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 compact and front-loaded with the core purpose and safety property, then gives usage guidance, names the alternative, and discloses best-effort behavior. Every sentence earns its place and there is no filler or repetition of schema details.

  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 read-only snapshot tool with all-optional parameters, a rich schema, and clear annotations, the description covers purpose, when to use it, when to prefer a sibling, and return behavior. Even without an output schema, the description's mention of 'bounded evidence' plus collection errors is sufficient context for correct invocation.

  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% parameter description coverage with detailed meanings, defaults, and bounds, so the baseline is 3. The description adds high-level semantic grouping like 'raw stack, locals, registers, exception details, modules, or nearby instructions,' but it does not meaningfully expand on individual parameters beyond what the schema already documents.

  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 states a specific verb and resource: 'Capture bounded evidence from the current stopped debug state without resuming execution.' It clearly distinguishes itself from debug_diagnose_stop by noting that the sibling additionally provides ranked crash hypotheses and project-frame selection, so an agent can select the right tool without opening schemas.

  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?

  The description gives explicit usage context: 'Use this when an agent needs raw stack, locals, registers, exception details, modules, or nearby instructions.' It also names the alternative condition: 'prefer debug_diagnose_stop when you also want ranked crash hypotheses and project-frame selection.' This is clear, actionable routing guidance.

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

• debug_source_disassemblyA
  4.7/5.0
  Behavior5/5

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

  Beyond the annotations, the description adds behavioral guarantees: it does not resume the target, it returns frame-selection reasoning, correlations, operand bindings, and it discloses best-effort collection errors. The 'read-only' statement aligns with annotations and adds no contradiction.

  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 dense sentences cover purpose, usage context, sibling alternative, constraints, and return contents. There is no filler, and the most important information is front-loaded.

  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?

  No output schema exists, but the description enumerates what the tool returns: frame-selection reasoning, both correlations, operand bindings, and collection errors. Combined with full schema parameter documentation and sibling differentiation, an agent has what it needs to invoke this 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 carries the parameter meaning. The description adds high-level context about project-controlled frames and provenance but does not need to repeat parameter details. 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 states a specific verb ('correlate') with concrete objects (source locations, disassembly, registers, pointer-like locals) and identifies the exact frames analyzed. It also distinguishes itself from debug_diagnose_stop by naming the depth of analysis, so an agent can immediately tell them apart.

  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?

  It explicitly says when to use the tool ('when a crash is already stopped and instruction/operand provenance matters') and when to prefer the sibling tool ('prefer debug_diagnose_stop for a broader ranked diagnosis'). This gives the agent clear routing among sibling tools.

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

• debug_statusA
  4.9/5.0
  Behavior5/5

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

  Annotations already mark the tool as read-only, idempotent, and non-destructive, and the description reinforces this with 'without changing target execution' and 'diagnostic only'. It adds useful behavioral context beyond annotations, such as bounded adapter stderr and the explicit list of actions it will not perform.

  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 with no wasted words. It front-loads the core purpose, then immediately provides usage context and exclusions. Every clause adds value and helps the agent decide correctly.

  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 parameterless diagnostic tool with strong annotations and no output schema, the description fully covers what it inspects, why to use it, and what it will not do. No additional context is needed for correct selection and invocation.

  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 tool has zero parameters, so parameter semantics are trivially covered by the schema. The description appropriately focuses on behavior and usage rather than parameters, matching the baseline for parameterless tools.

  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 states a specific verb ('Inspect') and concrete resources: debugger lifecycle state, selected stop, recent DAP events, and bounded adapter stderr. It explicitly distinguishes itself as diagnostic-only and clarifies that it does not resume, launch, attach, or terminate, which differentiates it from the sibling debug tools.

  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?

  It tells the agent exactly when to use it: before choosing another debug tool, to determine whether the session is initialized, running, stopped, postmortem, exited, or failed. It also gives clear exclusions by stating it does not resume, launch, attach, or terminate, guiding the agent toward alternative tools for those actions.

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