Server Quality Checklist

Tool Scores

• list_appsA
  3.7/5.0
  Behavior3/5

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

  Annotations already cover safety (readOnlyHint, openWorldHint, idempotent, non-destructive). The description adds useful scope detail ('currently running, non-background') but reveals nothing about output format, ordering, or the open-world nature of the result.

  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?

  One sentence conveys the action, scope, and output in a compact, front-loaded way. 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 zero-parameter read-only tool, this is nearly complete: it specifies the output is names of running non-background applicationsholový and annotations confirm safety. The only small gap is the exact output format, but the description's wording strongly implies a list of strings.

  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?

  There are zero parameters肯 with an empty schema, so no parameter documentation is needed. The description does not add parameter-level meaning, but the baseline for zero-parameter tools is 4.

  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 has a specific verb ('List') and a clear resource ('names of currently running (non-background) applications'). It differentiates from list_processes by focusing on application names and excluding background processes, though it does not explicitly name sibling alternatives.

  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 clearly conveys when to use this tool: when you need names of running applications. It gives no explicit exclusions or comparisons with siblings like list_processes or get_frontmost_app, so guidance is implied rather than stated.

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

• get_frontmost_appA
  4/5.0
  Behavior3/5

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

  The readOnlyHint and idempotent annotations already establish safety, and the description adds only that the result is a name. It does not contradict annotations, but also does not disclose edge-case behavior or system-specific limitations.

  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?

  One clear, front-loaded sentence communicates the tool's purpose without filler or unnecessary detail.

  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 simple read-only, no-parameter tool, this is nearly complete. It could optionally mention behavior when there is no frontmost application, but the description covers the core invocation context well.

  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?

  There are no parameters, so parameter documentation is not needed. The description appropriately focuses on what the tool returns rather than input semantics.

  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 and object: "Return the name of the frontmost (active) application." This distinguishes it from sibling tools like list_apps, list_processes, and system_info.

  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?

  Usage context is implied by the tool's name and description, but there is no explicit guidance about when to choose this over sibling tools or what to do when no frontmost application exists.

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

• list_processesA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so safety is covered. The description adds the ordering behavior ('busiest first') which is not in annotations, providing useful context beyond the structured metadata. It doesn't mention return format or error conditions, but for a read-only list tool, the description adds sufficient behavioral detail.

  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, front-loaded sentence that states the action, the resource, the returned fields, and the ordering. There is no redundant or unnecessary text; every word adds value. Excellent conciseness.

  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 read-only tool with two optional parameters and no output schema, the description covers the essential information: what is returned and how results are ordered. It does not explain pagination or platform variations, but these are minor for such a simple tool. The description is complete enough for an agent to invoke it correctly without additional guidance.

  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%: both 'limit' and 'filter' have clear descriptions in the schema. The tool description adds no additional parameter context beyond what the schema provides. Since the schema fully documents the parameters, the baseline of 3 applies.

  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 (list) and resource (running processes) and enumerates the returned fields (pid, cpu%, mem%, command). It clearly distinguishes from siblings like list_apps (apps) and system_info (system-level metrics) by focusing on process details. This is a precise, unambiguous purpose.

  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: if you need process-level details with CPU/memory usage, use this tool. However, it does not explicitly state when NOT to use it or point to alternatives. With siblings like list_apps and system_info present, the guidance is implicit rather than explicit, so a 3 is appropriate.

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

• get_clipboardA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds modest context by specifying 'text contents' and 'macOS', but it does not disclose potential edge cases like empty clipboard or permission requirements. 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?

  A single clear sentence contains all necessary information with no filler. It is appropriately sized for such a simple tool.

  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 zero-parameter, read-only operation with strong annotations, the description is complete. It states what is returned (current text clipboard contents) and the platform (macOS), which is all an agent needs to invoke it 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?

  The tool has zero parameters, so the baseline is 4. The description correctly scopes what is read ('text contents') but has no parameter meaning to add because no parameters exist.

  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 a specific verb ('Return') and names the exact resource ('current text contents of the macOS clipboard'). It is clearly distinct from sibling tools like read_file, list_directory, and get_frontmost_app, 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 Guidelines3/5

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

  The purpose strongly implies when to use it: whenever the agent needs the current text from the macOS clipboard. However, it does not explicitly state when not to use it or mention alternatives among the sibling tools, so the guidance is implied rather than explicit.

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

• read_fileA
  4.2/5.0
  Behavior4/5

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

  Annotations already establish read-only, idempotent, non-destructive behavior, so the description adds value by disclosing the size cap and the path allowlist constraint. It could say more about what happens on allowlist failure or oversize files, but it covers the key behavioral traits beyond 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?

  Two short sentences, each carrying necessary information: what is read, the cap, and the allowlist. No filler, front-loaded with the primary action.

  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 single-parameter, read-only tool, the description covers the essential constraints: target is a text file, capped size, and allowlist requirement. It does not detail error behavior or return format, but the operation is simple enough that the description is largely sufficient.

  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's parameter description already covers path syntax including '~'. The tool description adds that the path must correspond to a text file and must be allowlisted, which are meaningful constraints on the parameter's accepted values.

  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 the exact verb and resource: 'Read a text file's contents', which is more specific than the title and distinguishes it from sibling tools like list_directory and get_clipboard. It also adds two scope constraints (byte cap and allowlist) that define what this 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 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 a text file's contents. However, it does not explicitly state when not to use it or name alternatives; the allowlist mention hints at a prerequisite but no exclusions are given.

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

• list_directoryA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds meaningful behavioral context beyond annotations: it discloses the path allowlist restriction and specifies the return entries (name, type, size). It stops short of describing error behavior, but the annotation coverage lowers the bar.

  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 compact sentences: the first front-loads the action and output, the second states the key constraint. No filler or redundant repetition of the schema.

  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 single-parameter, read-only listing tool with strong annotations and no output schema, the description is complete enough for correct invocation. It covers what the tool returns, the path allowlist, and the required input. Minor omissions like sorting or hidden-file handling are not essential.

  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 documents path with minLength and ~ support (100% coverage), so the baseline is 3. The description adds the allowlist restriction, which is a valuable constraint on valid path values not present in the schema, pushing it above baseline.

  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, 'List', and a clear resource: directory entries including name, type, and size. This unambiguously differentiates it from siblings like read_file (file contents) and list_processes (running processes).

  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 intended use is implied by the name and action but never made explicit. There is no mention of when to choose this tool over alternatives, no exclusion criteria, and no routing to a sibling. The allowlist constraint hints at a condition but does not guide usage decisions.

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

• screenshotA
  4.3/5.0
  Behavior4/5

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

  The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable operational context beyond annotations: the tool returns a PNG and requires Screen Recording permission for the host process.

  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 short, front-loaded sentences. The first states the action and output; the second states the key prerequisite. No filler or repetition of schema content.

  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 zero-parameter tool, the description is complete: it explains what is captured, the output format, and the permission required. The annotations cover safety/idempotency, and there is no output schema that would require return-value documentation.

  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?

  There are zero parameters, so per the rubric the baseline is 4. The description correctly indicates that no configuration is needed—just capture the screen.

  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 the screen' and specifies the output format ('PNG image'). It is clearly distinguishable from all sibling tools, none of which capture the screen.

  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 tool's intended use is implied by its name and description, but there is no explicit statement of when to use it versus alternatives, nor any when-not-to-use guidance. The permission requirement is a prerequisite, not usage guidance.

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

• system_infoA
  4.3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds modest value by naming the exact categories returned, but it does not disclose operational details such as output format or timing. This is acceptable for a zero-parameter read-only tool, but it does not exceed the baseline.

  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 one sentence with a leading verb and a compact list of deliverables, containing no filler or redundant restatements of the title. Every phrase 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?

  Given the tool has zero parameters, no output schema, and clear safety annotations, the description is complete enough for an agent to select and call it correctly. It enumerates all the information categories the tool reports, which is all an agent needs for this simple read-only snapshot.

  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 input schema is empty with 100% coverage, so there are no parameter semantics to clarify. Following the 0-parameter baseline, the description does not need to compensate, and listing the reported data categories is more than sufficient.

  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 ('Report') and enumerates a precise set of system data: macOS version, hardware, memory, load, uptime, and current user. This clearly distinguishes it from siblings like list_processes, get_clipboard, and list_apps by content, even though it does not name them.

  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 implies use when an agent needs a high-level snapshot of macOS system state, and the readOnlyHint annotation reinforces that it is a safe diagnostic tool. It does not explicitly state when not to use it or name alternatives, but no sibling covers this exact aggregate of system information and there are no preconditions.

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