Server Quality Checklist

Tool Scores

• whats_downA
  3.9/5.0
  Behavior4/5

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

  Discloses that it returns active incidents first then resolved, which is behavioral. No annotations are provided, so description carries full burden, but it doesn't explicitly state read-only nature or idempotency. However, 'Check' suggests read-only.

  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, front-loaded with key info, no fluff.

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

  Completeness3/5

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

  Explains ordering but omits detail on incident fields returned. With no output schema, description should compensate more.

  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% and description adds no additional meaning to the limit parameter beyond what the schema already 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?

  The description uses specific verb 'Check' with resource 'outages or incidents', and specifies ordering (active first). It distinguishes from sibling tools check_service, get_incident, list_services by focusing on current incidents.

  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?

  Implies usage for current status overview, but does not explicitly state when to use vs check_service for specific service or get_incident for details.

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

• check_serviceA
  4/5.0
  Behavior4/5

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

  No annotations, but description clearly indicates a read operation without side effects. Does not contradict any structured data.

  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?

  Single sentence, front-loaded with purpose, 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?

  Adequate for a simple tool with one parameter and no output schema. Could mention output format or freshness, but not critical.

  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 covers 100% of parameter description. Description adds examples but no new semantics 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?

  Clear verb 'Check' and resource 'outage status and recent incident history of a specific service' with examples. Distinguishes from siblings like get_incident and list_services.

  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?

  Implied usage for checking a specific service's outage status, but no explicit guidance on when to use vs siblings or prerequisites.

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

• list_servicesA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description must fully convey behavioral traits. It states that it lists services with incident counts, implying a read operation with aggregated data. However, it does not explicitly confirm it is read-only, nor disclose any potential side effects, rate limits, or data freshness considerations. Basic transparency, but lacking explicit safety cues.

  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, concise and front-loaded with the core action 'List all services'. Every word adds value, with no redundancy or fluff. Ideal length for a simple 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?

  Given no output schema, the description adequately indicates the return type: services with incident counts. The tool is simple with no parameters, so the description covers the essential behavior. Could marginally improve by clarifying the default sort order or whether it includes all services regardless of status, but it is sufficiently complete for the complexity level.

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

  Parameters5/5

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

  The input schema has zero parameters, so schema description coverage is 100% (trivially). The description adds no parameter details because none are needed. It correctly describes what the tool does without requiring parameter explanations. This meets the baseline and exceeds it by being perfectly sufficient for a parameterless tool.

  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 'List all services monitored for outages, with lifetime incident counts.' It specifies the verb 'list', the resource 'services', and the scope 'all monitored' with additional detail 'incident counts'. This distinguishes it from siblings like 'check_service' (targets a specific service) and 'whats_down' (likely current status only).

  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?

  No explicit when/when-not advice or alternatives are given. The purpose is clear enough to infer usage, but the description does not guide the agent on when to prefer this over 'whats_down' or other list variants. Implicit 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.

• get_incidentA
  4.2/5.0
  Behavior3/5

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

  No annotations; description adds that it includes AI root-cause analysis when available, but doesn't address auth, rate limits, or side effects (though it's a read operation).

  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?

  Single sentence, no unnecessary words, front-loaded with action and resource.

  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 single-param read tool, description covers purpose and key output detail (AI analysis) but could mention that output is an incident object.

  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 100%; description adds meaning that 'slug' can be slug or numeric id and clarifies origin from sibling tool outputs.

  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?

  Clear verb 'get' with specific resource 'incident' by slug/id, and distinguishes from siblings like 'check_service' by focusing on incident detail.

  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?

  Specifies input source (slug from whats_down/check_service) and that it provides full detail including AI analysis, but lacks explicit when-not or alternatives.

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