Server Quality Checklist

Tool Scores

• pipeline_designC
  2.8/5.0
  Behavior2/5

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

  No annotations are provided, so the description bears full responsibility for disclosing behavior. It only says it 'executes' the pipeline and 'generates' code, without mentioning whether it is long-running, has side effects, or requires specific inputs. It also fails to describe the return format or any error behavior.

  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 sentence that front-loads the main action and uses a parenthetical list to enumerate pipeline stages. It is informative but somewhat lengthy at 30 words; still, every element adds context about the tool's scope.

  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 tool's complexity (a multi-stage pipeline) and the absence of both annotations and an output schema, this description is insufficient. It provides a high-level overview but omits critical details such as required inputs, parameter meanings, and expected output structure, making it hard to invoke correctly.

  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?

  The schema has only 17% description coverage, and the description itself lists no parameter information. Only 'componentCode' has a description in the schema; the other 5 parameters are completely undocumented. The description does not map the pipeline stages to input parameters, leaving the agent without adequate semantics.

  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 it 'Executes the unified multi-agent design pipeline' and outputs 'clean, production-ready Arabic/Bilingual UI code,' which clearly identifies the tool's function. However, it does not differentiate from the sibling tool 'run_full_design_pipeline,' which appears to have an identical purpose, so it lacks sibling distinction.

  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 the tool is for running the complete design pipeline from brief to benchmark, but it provides no explicit guidance on when to choose this over alternatives like 'invoke_design_agent' or 'anti_slop_audit.' There is no mention of exclusions or specific use cases.

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

• design_tokensC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries full responsibility for disclosing side effects and safety traits. It states that the tool generates tokens, but does not mention whether it writes files, returns data, requires authentication, or has any rate limits or limitations. This lack of detail makes the tool's runtime behavior opaque.

  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 sentence that efficiently packs in the core action and a wide range of capabilities and output targets. It is front-loaded with 'Generates' and avoids unnecessary repetition, though the phrase 'ultra-premium Claude Level-5' adds minor promotional fluff.

  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 tool with five parameters, no annotations, and no output schema, the description should explain what the tool returns and how parameters affect the output. It only enumerates what the tokens include and supported formats, providing no invocation-level details. This is insufficient for correct usage.

  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 only 40% (two of five parameters have descriptions). The description hints at the 'format' parameter by listing output formats (Tailwind v4, CSS, JSON, Flutter) and at color parameters via 'OKLCH color palettes', but it does not explain 'brandName' or 'themeMode'. This leaves most parameters underspecified.

  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 'Generates' and clearly identifies the resource 'design tokens' with detailed specifications (OKLCH color palettes, semantic layers, glassmorphism shadows, motion physics, Arabic typography scales). It also lists concrete output formats (Tailwind v4, CSS, JSON, Flutter), which clearly distinguishes it from sibling tools like anti_slop_audit or accessibility_audit.

  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 on when to use this tool versus alternatives such as generate_claude_design_tokens or run_full_design_pipeline. The intended usage is only implied by the tool's action, and there are no exclusions or comparative context.

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

• generate_rtl_ltr_layout_matrixB
  3/5.0
  Behavior3/5

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

  With no annotations, the description carries the transparency burden. It does disclose the core conversion behavior and specific features like icon flip and Form BiDi rules, but it does not mention return behavior, side effects, error modes, or how the output is delivered. This is adequate but incomplete.

  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, front-loaded with the action verb, and includes the key transformation details with no redundant filler. It is very efficient and easy to parse.

  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 4-parameter tool with no output schema and no annotations, the description is too brief. It leaves targetFormat and primaryDirection undefined, gives no usage guidance, and does not state what the tool returns. The agent may not be able to invoke it correctly.

  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 already documents componentSnippet and flipDirectionalIcons, and the description reinforces those. However targetFormat and primaryDirection have empty schema descriptions, and the description does not explain their meaning. At 50% schema description coverage, the description only partially compensates, so parameter semantics are weak.

  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 ('Converts') and identifies the resource ('legacy physical CSS/Tailwind/Flutter component code') with a clear output ('modern bidirectional logical components with directional icon flip and Form BiDi rules'). It clearly states the tool's purpose, though it does not explicitly differentiate it from sibling tools like rtl_layout_matrix.

  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?

  No guidance is provided on when to use this tool versus alternatives such as rtl_layout_matrix or design_tokens. The description does not mention prerequisites, exclusions, or appropriate use cases, leaving the agent without selection criteria.

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

• generate_claude_design_tokensB
  3.1/5.0
  Behavior3/5

  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 does add context about what the generated tokens include (OKLCH palettes, glassmorphism, etc.) and output targets, but it omits important behavioral details such as whether the tool writes files, returns output directly, or has side effects. No contradictions exist 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 sentence, front-loaded with the primary action ('Generates') and then listing token categories and formats. It is reasonably concise and well-structured, though the phrase 'ultra-premium' adds little informational value and could be considered fluff.

  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?

  The tool has 5 optional parameters, low schema coverage, no output schema, and no annotations, so the description must carry significant explanatory weight. It explains what is generated but does not cover return values, parameter roles, prerequisites, or how to combine with sibling design tools. This is insufficient for a complex generation tool.

  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 description coverage is only 40% (accentColor and primaryColor have descriptions), which is low. The description does not mention or explain any parameters, nor does it clarify how input values map to the generated token categories. It fails to compensate for the sparse schema information.

  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 clearly states the tool 'Generates ultra-premium Claude Level-5 design tokens' and lists specific token categories and output formats, making the purpose specific and actionable. However, it does not explicitly differentiate itself from the sibling tool 'design_tokens', which could cause confusion for the agent.

  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 through the listed output formats (Tailwind v4, CSS, JSON, Flutter) and token types, but it does not provide explicit guidance on when to choose this tool over alternatives like 'design_tokens' or when not to use it. The context is present but not stated as clear usage rules.

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

• invoke_interactive_design_agentB
  3.1/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits. It says 'dispatches' and lists outcomes, but it does not describe what 'interactive' means, whether the call is synchronous, how the response is formatted, or any side effects or requirements. This leaves significant ambiguity about runtime behavior.

  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, information-dense sentence that quickly states the action and lists the five agent personalities. It is not overly verbose, but the parenthetical list makes it slightly clunky. Overall it earns its place with relevant specifics.

  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 no output schema and no annotations, the description must convey return format and interaction behavior. It mentions expected outcomes ('deep design critique, strategic guidance, and code optimizations') but does not explain how the response is delivered, what 'interactive' means, or how parameters are used together. These gaps make it incomplete for a moderately complex 4-parameter tool.

  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 covers all 4 parameters with descriptions (100% coverage), so the baseline is 3. The tool description adds no extra parameter-level meaning beyond the schema; it only implies that codeSnippet may relate to 'code optimizations' but doesn't explicitly connect them.

  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 clearly states the tool's job: 'Dispatches design challenges to specialized adaptive AI design agents' and lists the exact agent personas. This distinguishes it from the generic sibling 'invoke_design_agent', but it does not explicitly contrast with that or other siblings, and the word 'interactive' in the name is not explained.

  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 when design challenges need critique, strategy, or code optimization, and the listed agent names suggest domain-specific use. However, it does not state when to use this tool versus alternatives, nor does it give any exclusion criteria or mention sister tools like 'invoke_design_agent' or 'anti_slop_audit'.

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

• arabic_typographyB
  3.2/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden for behavioral disclosure. It does enumerate the audit dimensions (optical alignment, font pairing, line-height compensation, ligature integrity), which gives some insight into behavior, but it does not disclose output format, side effects (though likely none), or any constraints.

  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, information-dense sentence with no filler. It front-loads the action and clearly enumerates the audit areas, achieving high conciseness.

  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?

  The tool has five parameters, no output schema, and no annotations. The description fails to explain what the audit produces (e.g., a report, score, recommendations) and does not clarify the meaning of `targetPlatform`. Additionally, the existence of the sibling `analyze_arabic_typography` creates ambiguity that is not resolved.

  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 80% (4/5 params have descriptions), so baseline is 3. The tool description does not add any parameter-specific meaning beyond the schema, and `targetPlatform` remains unexplained in both schema and description.

  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 ('Audits') and resource ('Arabic or bilingual text snippet') with four concrete focus areas. However, it does not differentiate from the similarly named sibling 'analyze_arabic_typography', so it falls short of a 5.

  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?

  No guidance is provided about when to use this tool versus alternatives such as 'analyze_arabic_typography' or 'audit_bilingual_accessibility'. There is no mention of when-not-to-use or prerequisites, so this dimension scores poorly.

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

• rtl_layout_matrixB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what the tool does (converts code, flips icons, applies Form BiDi rules) but does not disclose side effects, whether it is read-only, output format, limitations, or required permissions. This is a significant gap for a conversion tool.

  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 dense sentence that front-loads the main action and purpose. It includes all key features without excessive filler. The structure is acceptable, though the sentence is somewhat long and could be split for readability.

  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 no output schema, the description should explain what the conversion returns or how output is structured, but it does not. It also leaves two parameters undocumented and provides no guidance on output format or usage examples. The lack of return-value documentation and vague parameter handling make the description incomplete.

  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 50%, with targetFormat and primaryDirection having empty descriptions. The tool description does not compensate by explaining allowed values or meaning for these parameters. It adds some context for flipDirectionalIcons ('directional icon flip') but leaves the core parameters ambiguous, hindering correct invocation.

  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 action ('Converts') and a specific resource ('legacy physical CSS/Tailwind/Flutter component code') with a clear outcome ('modern bidirectional (RTL/LTR) logical components'). It also mentions distinctive features (directional icon flip, Form BiDi rules) that separate it from audit or analysis sibling tools.

  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 the tool (when you have legacy physical component code to convert to bidirectional logical components) but does not explicitly mention alternatives or when not to use it. No clear exclusionary guidance is provided, so usage is inferred rather than explicitly stated.

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

• accessibility_auditB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description bears full responsibility for behavioral disclosure. It states what the tool audits but does not reveal whether it is read-only, requires permissions, has side effects, or what the output format is. This leaves a significant transparency gap.

  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 efficiently lists the core action, resource, and specific audit criteria without any filler. Every element earns its place.

  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 no output schema and no annotations, the description should explain what the audit returns, how parameters influence it, and any prerequisites. It lacks all such context, making it incomplete for an agent to decide on invocation and interpret results.

  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 only 33% (only 'markup' has a description). The tool description does not compensate by explaining 'checkContrast' or 'checkBidiSemantics' or how they relate to the audit. Since coverage is low, the description should have added meaning, but it does not.

  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 verb 'Audits' and the resource 'HTML/JSX code markup', then enumerates specific checks (dir="rtl", lang="ar", BiDi, touch targets, focus rings, WCAG 2.2 AA). This makes the tool's purpose highly specific and distinguishable from generic audits.

  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 for auditing Arabic accessibility, but it does not provide explicit when-to-use/when-not-to-use guidance or mention alternatives like audit_bilingual_accessibility. The context is clear but lacks exclusionary or comparative info.

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

• run_full_design_pipelineB
  3.4/5.0
  Behavior2/5

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

  No annotations exist, so the description alone is responsible for behavioral disclosure. It mentions the multi-agent execution and output of clean UI code, but does not mention prerequisites, side effects, execution duration, or any failure/error behavior. It also lacks indication of whether inputs are required, making behavioral expectations incomplete.

  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 well-structured sentence, front-loaded with the core action and followed by a clear stage list. It conveys significant information without fluff, though the long arrow chain might be slightly dense.

  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 complexity of a 6-parameter multi-agent pipeline with no output schema, this description is insufficiently detailed. It lacks a definition of the return value, input responsibilities, or constraints, and does not compensate for the schema and annotation gaps.

  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 only 17% (only `componentCode` has a description), and the tool description does not discuss any of the six parameters. While the overall context hints at design inputs (brand, fonts, colors), the description adds no semantic meaning to the parameters, leaving the agent to infer from names alone.

  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 specifies the verb 'Executes' and the resource 'unified multi-agent design pipeline', clearly distinguishing it from individual stage tools like `arabic_typography` or `anti_slop_audit`. It also enumerates the pipeline stages, removing ambiguity about its scope.

  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 for an end-to-end design process by listing all stages from Brief Inference to Benchmark. However, it does not explicitly state when not to use it or direct to alternative tools for individual stages, so guidelines are clear but not explicit.

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

• invoke_design_agentA
  3.5/5.0
  Behavior2/5

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

  With no annotations, the description must disclose behavioral traits, but it only states that challenges are 'dispatched' to get critique. It does not explain the response format, whether the agents are synchronous/asynchronous, any side effects, or what the actual output looks like. This is insufficient for an agent-invoking tool.

  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, dense sentence with no fluff. It includes a parenthetical list of agent names, which is informative though slightly packed. The structure front-loads the verb and resource, keeping it concise.

  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?

  The tool has four parameters, no output schema, and no annotations, so the description bears a heavy burden. It fails to explain how to choose an agentRole, what the output structure resembles, or how this differs from invoke_interactive_design_agent. The omission leaves the agent without enough context to invoke the tool confidently.

  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 coverage is 100%, so baseline is 3. The description adds value by enumerating the agent personas, giving concrete options for agentRole, and implicitly linking codeSnippet to 'code optimizations.' This goes beyond the schema's generic descriptions, but it does not clarify other parameters like projectContext.

  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 dispatches design challenges to specialized AI agents, naming them explicitly (ArabicArtDirector, RTLArchitect, etc.) and listing the intended outcomes (deep design critique, strategic guidance, code optimizations). This distinguishes it from other design-related tools like anti_slop_audit or pipeline_design by focusing on agent-based consultation.

  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 for design challenges requiring agent personas, but it provides no explicit when-to-use or when-not-to-use guidance, nor does it name alternatives. It is not misleading but lacks direct context for choosing this tool over invoke_interactive_design_agent or other audit tools.

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

• analyze_arabic_typographyA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description carries the transparency burden. It lists audit dimensions but does not state that the tool is read-only, what the output format is, or any side effects. The verb 'audits' implies non-destructive analysis, but this is not explicit.

  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, efficient sentence that front-loads the verb and specifies exactly what is checked. No filler.

  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?

  No output schema exists, and the description does not describe the return value or structure of the audit report. It also omits any behavioral prerequisites or limitations, such as whether the audit supports mixed-language snippets or requires specific font availability.

  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 80% with four of five parameters described. The tool description does not directly map its audit dimensions to parameters, but the schema itself is mostly self-explanatory, so baseline 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 clearly states a specific verb 'Audits' and identifies the resource as 'an Arabic or bilingual text snippet,' listing four concrete auditing dimensions. This distinguishes it from sibling tools like 'arabic_typography' which may focus on typography generally rather than auditing.

  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-to-use or alternative guidance is provided. Usage is implied by the audit verb, but the description does not clarify when to choose this over 'arabic_typography' or 'audit_bilingual_accessibility.'

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

• audit_bilingual_accessibilityA
  3.6/5.0
  Behavior4/5

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

  With no annotations, the description carries full burden. It discloses specific audit checks (BiDi text isolation, touch targets, focus rings, WCAG 2.2 AA), giving insight into behavior. However, it does not describe return format or explicitly confirm that it does not modify input, though 'audits' implies analysis.

  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 lists all key audit areas without fluff. It is front-loaded with the core purpose. While slightly dense, every phrase adds value and the structure is efficient for an audit tool description.

  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?

  The description omits necessary context: parameter semantics for two of three params, output/return format, and any caveats. Given no output schema or annotations, the description alone is insufficient for an agent to confidently invoke the tool with correct parameter values.

  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 coverage is only 33% (only 'markup' has a description). The description adds meaning to 'markup' but provides no detail on 'checkContrast' or 'checkBidiSemantics' — their expected values or semantics remain unclear. The tool description does not compensate for the schema's 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 specifies a unique verb ('audits') and resource ('HTML/JSX code markup') with a specific scope (Arabic screen reader compatibility, BiDi, touch targets, focus rings, WCAG 2.2 AA). This distinguishes it from generic siblings like 'accessibility_audit' and other Arabic-focused tools.

  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 for Arabic-specific accessibility auditing but does not explicitly state when to use this tool versus alternatives like the generic 'accessibility_audit'. No exclusions or alternative recommendations are mentioned.

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

• evaluate_design_benchmarkA
  3.6/5.0
  Behavior3/5

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

  Without annotations, the description carries the transparency burden. It discloses return values but does not explicitly state side-effect-free behavior, limitations, or any required context. The verb 'evaluates' implies read-only, but the description could be more explicit about its safe, non-mutating nature.

  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, well-structured sentence that efficiently covers the action, target standard, input types, and output categories. 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?

  Given the absence of an output schema and annotations, the description sufficiently explains what the tool returns. However, it lacks any usage context or differentiation from sibling tools, making it slightly incomplete for a tool in a crowded design-related ecosystem.

  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 each parameter already has a description. The tool description adds no extra parameter-specific meaning beyond what the schema provides, though it confirms the input types mentioned in the codeOrMarkup 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 clearly states the tool's function: evaluating UI code, CSS, or Tailwind markup against Level-5 Claude Design standards. It also lists returned artifacts (overall score, sub-scores, strengths, recommendations), which distinguishes it from sibling audit tools like anti_slop_audit and accessibility_audit.

  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?

  No guidance is provided about when to use this tool versus alternatives. It doesn't describe ideal scenarios, exclusions, or how it relates to sibling tools such as pipeline_design or invoke_design_agent, leaving usage entirely to inference.

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

• anti_slop_auditA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses specific behavioral aspects by listing the violation types it checks, which is useful. However, it does not state whether the audit is read-only, whether it modifies code, or what the output format is. This missing information is notable for a tool with no 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?

  The description is a single, information-dense sentence that lists the purpose and four concrete checks without any filler. Every word earns its place, making it highly concise and well-structured.

  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 tool has one parameter, no output schema, and no annotations. The description explains what the tool does but omits critical operational details such as the return format (e.g., list of violations, pass/fail), whether it is destructive, or any side effects. Given the simplicity, the missing output behavior is a clear gap, but the purpose is sufficiently precise to make the tool usable at a basic level.

  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% (the codeSnippet parameter is described as 'The UI code snippet to audit against anti-slop rules'). The tool description adds general context about what the audit checks but does not provide additional meaning specifically about the parameter format or processing expectations beyond the schema. 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 uses a specific verb ('Audits') with a clear resource ('UI code') and scope ('anti-AI-slop violations'), listing four concrete violation types (em-dash bans, rounded left-border cards, fake metrics). This clearly distinguishes it from sibling audit tools like accessibility_audit or audit_bilingual_accessibility.

  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 the tool (when auditing for anti-slop rules) but does not explicitly state when not to use it or mention alternative tools. No exclusions or alternatives are provided, leaving the usage context implicit rather than explicit.

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