Server Quality Checklist

Tool Scores

• search_nodesC
  2.9/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=false, so the description's job is to add context beyond that. It adds little beyond restating the read-only search behavior, though for a simple search tool there is limited behavior to disclose. 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.

  Conciseness4/5

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

  A single sentence with zero wasted words, and the core action is front-loaded. It is efficient, though it borders on under-specification rather than true concision.

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

  Completeness2/5

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

  For a search tool with no output schema and a sibling (inspect_node_type) that overlaps in domain, the description should clarify scope and the meaning of the limit parameter. It does neither, leaving an agent to guess about result behavior and when this tool is the right choice.

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

  Parameters2/5

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

  The schema has 0% description coverage, so the description must compensate for explaining the parameters. The description implies 'query' is a search term for node types, but it does not clarify the 'limit' parameter's semantics (pagination, result cap, or default behavior) at all. With two parameters undocumented, the description is insufficient.

  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 verb ('search') and a specific resource ('node types installed in ComfyUI'), making the core purpose clear. It does not explicitly distinguish itself from its siblings (especially inspect_node_type), but the verb choice implies a broad search versus targeted inspection, giving partial differentiation.

  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?

  There is no guidance on when to use this tool versus its siblings, no exclusions, and no named alternatives. An agent cannot tell from the description whether to use search_nodes or inspect_node_type for a given task, leaving the routing decision entirely to inference.

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

• inspect_canvasB
  3.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, so the read-only safety profile is covered. The description adds 'compact live' and 'native' context, which suggests the output is a condensed current-state view, but it does not disclose return format or behavior when no parameters are provided. 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.

  Conciseness4/5

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

  The description is a single front-loaded sentence with no wasted words. 'Compact live' and 'native' are dense but meaningful qualifiers, though they could be clearer.

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

  Completeness2/5

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

  With two optional parameters, no required fields, no output schema, and no usage guidance, the description does not sufficiently equip an agent to invoke the tool correctly. Missing details include the meaning of an all-empty call, the relationship between canvas_id and refs, and when to prefer sibling tools.

  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 already describes canvas_id and the refs kind/id shape. The description adds that refs target 'native node and group' details, which gives some meaning beyond the schema. However, it does not clarify whether canvas_id and refs are alternatives, complementary, or what happens when both are absent, leaving a partial gap at 50% schema coverage.

  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 names a clear action ('Inspect') and resource ('compact live ComfyUI canvas', 'node and group refs'), which distinguishes it from mutating or presenting siblings. The phrase 'or details for native node and group refs' is slightly ambiguous about the exact object of inspection, but the core purpose is understandable.

  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?

  The description gives no explicit guidance for when to use this tool versus search_nodes or inspect_node_type. It weakly implies that this tool is for reading canvas/ref state, but it does not state conditions, exclusions, or alternatives.

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

• inspect_node_typeB
  3.1/5.0
  Behavior3/5

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

  Annotations declare readOnlyHint=true and openWorldHint=false, and the description's 'Inspect' verb aligns with a safe read operation - no contradiction. The phrase 'complete native ComfyUI schema' adds modest context about the scope of what is returned. However, it doesn't describe output volume, error behavior for invalid class types, or whether the full schema is returned as structured JSON, so the value added beyond annotations is limited.

  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, tightly worded sentence with zero waste. The action and object are front-loaded with no filler or redundancy. Every word earns its place.

  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?

  For a simple one-parameter, read-only inspection tool with no output schema, the definition is borderline adequate. It clearly states what it does and the annotation covers the safety profile, but it leaves the agent to guess what class_type should contain and offers no usage guidance. Given the tool's low complexity and the sibling overlap, this is a minimum-viable definition that could be more complete.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description carries the full burden of explaining the parameter. The phrase 'one installed node type' weakly hints that class_type names a node type, but it never explicitly maps class_type to that concept, states its expected format, or notes that it must be an installed node type identifier. The description insufficiently compensates for the zero coverage.

  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 uses a specific verb ('Inspect') and identifies a clear resource ('the complete native ComfyUI schema for one installed node type'). This distinguishes it from siblings like inspect_canvas (canvas vs node type) and search_nodes (search vs inspect), though it doesn't name them explicitly. A 5 would require explicit sibling differentiation, so 4 is appropriate.

  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?

  The description provides no guidance on when to use this tool versus alternatives like search_nodes or inspect_canvas, and no prerequisites or exclusions are stated. The usage context is only implied by the purpose clause, so the agent receives no routing help.

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

• apply_canvas_patchB
  3.3/5.0
  Behavior4/5

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

  Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description discloses that changes are atomic (all-or-nothing), undoable, and applied to a live canvas. This adds meaningful behavioral context about failure semantics and reversibility, though it doesn't address concurrency conflicts or the role of base_revision.

  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, front-loaded sentence with no filler. Every word ('atomic', 'undoable', 'live', 'batch') earns its place by conveying behavioral and semantic constraints.

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

  Completeness2/5

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

  Given the destructive, non-idempotent nature and a complex operations schema with no output schema, an agent needs more context about conflict behavior, base_revision semantics, and typical use cases. The compact description covers a few key properties but leaves major gaps for correct invocation.

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

  Parameters1/5

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

  Schema description coverage is 0%, and the description does not compensate by explaining canvas_id, base_revision, or the operations array. It only says 'batch of changes,' which maps vaguely to operations but adds no meaning to any specific parameter.

  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 action ('apply'), a precise resource ('changes to a live ComfyUI canvas'), and adds defining qualifiers ('atomic, undoable batch') that set it apart from the sibling read/search tools. It tells an agent immediately that this is the mutating patch tool for canvas edits.

  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?

  There is no guidance about when to use this tool versus alternatives such as inspect_canvas, present_canvas, search_nodes, or inspect_node_type. The phrase 'apply ... batch of changes' implies mutating use, but it does not state prerequisites, when not to use it, or which sibling might be preferred.

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

• present_canvasA
  3.8/5.0
  Behavior3/5

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

  Annotations already provide destructiveHint=false and idempotentHint=true; the description adds that the workflow is not modified and that the operation targets live canvas state. However, it does not disclose how the selection is changed (replace vs add), what happens with invalid refs, or the effect of fit_view.

  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 efficient sentence with no filler. It front-loads the action and includes a useful constraint about not modifying the workflow. Every word earns its place.

  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?

  The description is adequate for a relatively simple 4-parameter tool with strong safety annotations, but it leaves some semantics implicit, especially selection behavior and fit_view. Without an output schema, the description also does not indicate what the agent should expect after invocation.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description carries the burden of explaining parameters. It only provides the overall intent and does not map canvas_id, refs, selection, or fit_view to concrete meanings. The enum values 'replace' and 'add' are left for the agent to infer from their names.

  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 action ('Select and optionally fit native items') and a specific resource ('live ComfyUI canvas'), and it explicitly scopes the operation as not modifying the workflow. This clearly distinguishes it from siblings like apply_canvas_patch (which modifies) and inspect_canvas (which reads).

  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 conveys when to use the tool: for selection and view-fitting on a live canvas while keeping the workflow unchanged. It gives a clear exclusion ('without modifying the workflow'), but it does not explicitly name sibling alternatives or state cases where inspect_canvas or apply_canvas_patch should be preferred.

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