Server Quality Checklist

Tool Scores

• delete_funnelA
  4.4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It clearly discloses the most critical behavioral trait: irreversibility ('Permanently delete' and 'Irreversible'). It stops short of describing permissions, error handling, or scope of deletion, but for a simple delete tool, this is solid coverage.

  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, with the action front-loaded and the warning immediately following. Every word earns its place, and the structure is highly efficient.

  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 one-parameter nature, the presence of an output schema, and the explicit irreversibility warning, the description is nearly complete. It could add details about permissions or failure outcomes, but these are not essential for a straightforward delete tool. The guidance to list first adds valuable context.

  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 0%, so the description must compensate. It indirectly explains funnel_id by saying 'by id' and recommending list_funnels to confirm the id. However, it does not explicitly describe the id format or provide details beyond the schema's title. For a single, self-explanatory parameter, this is adequate but not outstanding.

  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 exactly what the tool does: 'Permanently delete a trace funnel by id.' It uses a specific verb (delete), identifies the resource (trace funnel), and clearly distinguishes from sibling tools like list_funnels and create_funnel.

  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?

  Explicit guidance is provided: 'Use ``list_funnels`` first to confirm you have the right id.' This tells the agent when to use this tool relative to an alternative and even gives a prerequisite step, making usage clear.

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

• list_funnelsA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains that it lists all funnels and what fields are returned, which is a strong signal of a read-only operation. However, it does not mention potential limitations (e.g., pagination, filtering, auth) or whether 'every' truly means all across all scopes, leaving a minor gap. Still, for a zero-parameter list tool, the transparency is solid.

  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 core purpose and output, followed by a precise usage hint. Every word earns its place with no fluff or repetition.

  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 operation with zero parameters and an output schema, the description covers purpose, scope, and usage context sufficiently. The output schema handles return details, so the description does not need to explain them further. The explicit 'Start here' guidance ties it well to the sibling-tool context.

  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, and the description naturally omits parameter details. Per the rubric, a baseline of 4 applies when there are no parameters to describe, and this description does not need to compensate for any schema gaps.

  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 action ('List every SigNoz trace funnel') and the specific resource, including the returned fields (id, name, step definitions). It also differentiates from sibling tools by framing the use case ('need its id', 'check whether a funnel already exists before creating a duplicate'), which implies a read-only listing versus the create/delete/analytics 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?

  Explicitly states when to use this tool: 'Start here when you have a funnel name but need its id, or to check whether a funnel already exists before creating a duplicate.' This provides clear situational context and implicitly contrasts with the create_funnel sibling, satisfying the when/alternatives guidance.

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

• create_funnelA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden, and it excels. It exposes concrete implementation details: millisecond timestamps, mandatory 'timestamp' in update, omitting step 'id' to let SigNoz generate UUID, automatic cleanup of empty funnels on failure, and the caveat that 'p50' silently yields p99. This is far beyond what a typical tool description provides.

  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?

  Although lengthy, the description is well-organized with clear sections (Args, Returns, Note) and an example. Every sentence adds value—explaining undocumented requirements, defaults, and edge cases. There is no fluff, and the structure allows an agent to quickly locate parameter details and behavioral notes.

  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?

  The tool is complex (wrapping two REST calls, with tricky requirements), yet the description covers all significant aspects: purpose, parameters, return values, error handling, and limitations. The presence of an output schema is not necessary because the description already outlines what is returned (funnel_id, steps, warnings). It leaves no major gaps for an agent to fill.

  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 is minimal (name and steps, with steps as a generic array of objects). The description compensates fully by specifying each required and optional field inside a step (service, span, name, latency_type, has_errors), defaults, examples, and the meaning of 'latency_type' with the p50 caveat. It also gives a concrete example of the steps array, making parameter usage unambiguous.

  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's primary function: 'Create a SigNoz trace funnel and set its steps in a single call.' It names the specific resource (SigNoz trace funnel) and the verb (create/set), which distinguishes it from siblings like list_funnels, delete_funnel, and analytics tools. No ambiguity.

  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 explains the tool's scope by noting it wraps two REST calls and handles undocumented requirements, which implies this is the recommended way to create funnels. It also gives a key limitation: 'All steps must occur within the same trace' and that funnels cannot see loops/retries. However, it doesn't explicitly compare to alternatives or say 'use this when X'—though siblings are clearly different operations, so the guidance is adequate.

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

• get_funnel_analyticsA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and does so thoroughly. It discloses the SigNoz HTTP 500 NaN bug and zero_trace_fallback, the strict step ordering causing under-counts, the semantics of errors as a MAX, and latency hardcoded to p99. These are behavioral insights far beyond a basic operation description.

  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 structured with Args, Returns, and Notes sections, keeping details organized and front-loaded. Every sentence provides useful information, including edge-case caveats, without fluff. It is appropriately sized for the tool's complexity.

  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 an output schema (per context signals), the description still explains the return structure, parameter semantics, and critical gotchas. For a tool with this complexity—two identifying parameters, time-range conversion, and known SigNoz quirks—the description is fully complete and self-sufficient.

  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?

  Schema description coverage is 0%, so the description must explain all parameters. It does so completely: funnel_id (UUID), funnel_name (resolved to id, ignored if id given), and time_range (with examples and note about nanosecond conversion). This adds significant meaning beyond the bare schema properties.

  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 "Measure a funnel: per-step conversion with trace counts, plus end-to-end metrics," a specific verb+resource that clearly states what the tool does and distinguishes it from sibling tools like list_funnels, create_funnel, and get_funnel_slow_traces. The name and description together make the tool's function unambiguous.

  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 clear context for when to use the tool ('Measure a funnel...') and explains identification via funnel_id or funnel_name. It does not explicitly mention alternatives or when not to use this tool, but the context is sufficiently clear, so it meets the 'clear context, no exclusions' bar.

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

• get_funnel_slow_tracesA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses behavioral constraints: the hardcoded ORDER BY duration_ms DESC LIMIT 5 with no paging, the pairwise nature of the query, and the return shape including error_traces. This is exactly the kind of non-obvious behavior 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 front-loaded with a one-sentence summary, then organized into Args, Returns, and Note sections. Each sentence adds necessary context; the length is justified by the tool's complexity and the lack of annotations.

  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?

  The output schema is present (as indicated by context signals), but even without it, the description states the return format (up to 5 rows of trace_id, duration_ms, span_count plus error_traces) and key limitations. Combined with parameter semantics and usage guidance, it is fully contextual for an agent to select and invoke this tool.

  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?

  Schema coverage is 0%, but the description defines all 5 parameters with meaningful semantics: funnel_id as UUID, funnel_name as alternative, time_range as relative window ('24h'), and step_start/step_end as 1-based indices with the constraint that they must differ. This fully compensates for the bare 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 opens with a specific verb+resource: 'Fetch the slowest traces for one step transition of a funnel.' It clearly differentiates from siblings by positioning itself as the follow-up to get_funnel_analytics, providing trace IDs rather than analytics.

  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?

  Explicitly states when to use: 'Use this after get_funnel_analytics shows a drop-off or high latency between two steps.' It also clarifies scope (pairwise transition not whole funnel) and row limits, but does not explicitly name 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.