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

No annotations provided, so the description carries the full burden. It describes the content (examples, anti-patterns, etc.) and available tools but does not explicitly state it is read-only or has no side effects. However, the tone and purpose strongly imply it is a harmless guide retrieval.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two efficient sentences with a parenthetical list. No wasted words—every sentence earns its place. The key action and prerequisites are front-loaded.

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

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

For a simple one-parameter tool with no output schema, the description fully covers purpose, content, usage timing, and available options. No gaps remain for an AI agent to resolve.

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

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

Schema coverage is 100% (parameter tool_name has a description listing valid values). The main description reinforces these values, adding contextual meaning (e.g., 'or "all" for a summary'). This adds value beyond the schema's bare enumeration.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get usage guide for a rendering tool' and specifies it includes examples, anti-patterns, complexity limits, and tips. It differentiates from sibling rendering tools by being a guide retrieval rather than a rendering action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Explicitly advises 'Call this BEFORE your first render to avoid common mistakes,' providing clear when-to-use guidance. Also lists available tool names, helping the agent choose the correct parameter value.

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

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

No annotations provided. The description implies a read-only operation but does not disclose potential errors (e.g., missing directory) or behavior like recursion, leaving significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Extremely concise single sentence with no wasted words. Information is front-loaded and easy to parse.

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

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

For a simple, single-parameter tool, the description is adequate but lacks details on return format or error handling. Could be slightly more informative.

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

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

Schema coverage is 100% with a clear parameter description. The tool description adds no extra meaning beyond the schema, meeting baseline expectations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists all generated media assets in the output directory. It distinguishes from sibling tools (render tools) by focusing on listing rather than rendering.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool vs alternatives. It does not specify prerequisites or context, leaving the agent to infer usage.

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

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

No annotations exist, so description must cover behavior. It does not mention any side effects, permissions, rate limits, or return format. The agent cannot infer safety or operational constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Four concise sentences, front-loaded with purpose. Every sentence contains essential information without fluff. Efficient use of space.

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

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

No output schema and no annotations; the description covers core usage but omits return format and any behavioral context. Adequate but not thorough.

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

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

Schema coverage is 100%, but description enriches semantics: clarifies scale usage for retina output, specifies required fields in spec_json, and warns about anti-patterns. Adds real value beyond schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it renders Vega-Lite charts to SVG or PNG, with a specific verb and resource. It distinguishes from sibling tools like render_mermaid by naming the charting library and formats.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Lists supported chart types and anti-patterns, and references get_tool_guide for examples. Provides context on when to use, but lacks explicit exclusion of alternatives.

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

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

With no annotations, the description bears full burden. It discloses performance characteristics (PNG slower via Chromium), syntax restrictions (no Mermaid, limited nesting), and error-prone patterns. Missing details on error messages, output size limits, or throttling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Extremely concise: four sentences front-loading purpose, best-for, syntax, anti-patterns, and guidance. No wasted words; every sentence earns its place.

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

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

For a tool with 4 parameters (no output schema), the description is remarkably complete. It covers purpose, syntax, format selection, layout guidance, common mistakes, and points to examples. The agent can use this without confusion.

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

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

Schema covers all parameters (100%), so baseline is 3. Description adds value by explaining the ordering of layout engines ('dagre=hierarchical', 'elk=complex') and highlighting PNG speed tradeoff. These enrich the schema's enum descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Render a D2 architecture diagram to SVG or PNG' with a specific verb and resource. It distinguishes itself from siblings like render_mermaid by emphasizing D2's unique syntax and suitability for complex architecture diagrams.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Provides clear context: 'Best for: architecture diagrams with containers, nested groups, icons, and complex layouts.' Includes explicit anti-patterns and a reference to get_tool_guide for examples. Could be improved by explicitly stating when not to use (e.g., if the goal is a sequence diagram, use Mermaid).

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

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

Discloses syntax requirements (digraph G, -> vs --) and engine options with their typical uses. With no annotations, it carries the burden well, though tips on error handling or limits are missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Very concise: single paragraph with logical flow from purpose to use cases to important notes to engine guide to additional resources. No wasted words.

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

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

Given no output schema and moderate complexity (3 params), description covers syntax, engines, and use cases adequately. Minor omission: difference between SVG and PNG output.

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

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

Schema covers all parameters (100%), but description adds extra context: engine guide (e.g., 'sfdp=large graphs') and syntax rules. Adds value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States exactly what it does: 'Render a Graphviz DOT diagram to SVG or PNG.' Differentiates from siblings like render_mermaid and render_d2 by specifying Graphviz format.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Provides clear use cases: dependency graphs, network diagrams, tree structures, large auto-layout graphs. Also mentions calling get_tool_guide for examples, but does not explicitly exclude scenarios.

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

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

No annotations provided, so description carries full burden. It reveals that the tool wraps HTML in a design system, requires specific mf- prefixed CSS classes, and warns against including outer tags. It also mentions the themes and references get_tool_guide for details. No discussion of auth or rate limits, but those are less critical for a rendering tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, well-structured paragraph with no redundant information. Key points are front-loaded (what it does, no Docker) and all details are relevant. Every sentence adds value, making it concise yet comprehensive.

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

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

The tool has 5 parameters and no output schema. The description covers the main input constraints and provides a reference for more details. It could have mentioned the return value format (a complete HTML string), but overall it is sufficiently complete for the tool's simplicity and supported by the schema.

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

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

Schema coverage is 100%, but the description adds value by explaining usage beyond schema: e.g., body_html is 'inner content only', themes are expanded with contexts, nav_sections must match id attributes. This clarifies semantics beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool renders a self-contained themed HTML page from body content, mentioning key features like themes and CSS classes. It distinguishes from sibling tools like render_mermaid or render_slides by focusing on HTML page rendering and referencing get_tool_guide for design system details.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides clear when-to-use guidance (rendering a themed HTML page) and notes no Docker required. It gives important instructions about body_html content. However, it does not explicitly exclude use cases or list alternatives beyond the sibling tools.

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

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

No annotations provided, so description carries full burden. It discloses required syntax, anti-patterns (33+25 node warning), and output format preferences. This gives clear behavioral expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences plus bullet-like anti-pattern list. Front-loaded with purpose. Every sentence earns its place, no fluff.

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

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

Covers purpose, constraints, and output format. No output schema, but typical render tool returns image data. Could specify if output is base64 or file, but enough for agent to infer. Omits nothing critical.

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

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

Schema covers all 3 parameters with descriptions (100% coverage). Description adds value: suggests SVG for git-friendly diffs, theme use-cases (neutral for docs, forest for dark). Adds meaningful guidance beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Render a Mermaid diagram to SVG or PNG' and lists 10 supported diagram types, matching the tool name and distinguishing it from siblings like render_d2 or render_graphviz.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Provides explicit constraints: code must start with diagram type, no semicolons, no HTML tags, and warns against anti-patterns. Also directs to get_tool_guide for examples. Lacks explicit when-not-to-use vs alternatives, but sibling names imply context.

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

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

No annotations provided, so description carries full burden. Discloses key behaviors: self-contained output, navigation, transitions, and content density limits (max bullets, code lines, quote words, total slides). Does not cover error handling or idempotency, but provides useful constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Three sentences front-loaded with purpose and key features. No redundant words. Efficiently conveys essential information, with a call to action for additional details.

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

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

Covers purpose, constraints, and references external guide. Lacks details on output format (though implied) and error handling for limit violations. Given no output schema and 4 parameters, description is adequate but could be more thorough on edge cases.

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

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

Schema coverage is 100%, baseline 3. Description adds value by explaining that 'slides' is a JSON array string with specific structure and optional type, and includes content density limits per slide type, which go beyond the schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool renders a self-contained HTML slide deck with specific features (keyboard navigation, progress bar). The verb 'render' and resource 'slide deck' are explicit. Distinguishes from sibling tools like render_mermaid and render_chart by focusing on slides.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Mentions 'No Docker required' as a contextual note, suggesting alternatives might require Docker. Directs users to call get_tool_guide('slides') for more info, but does not explicitly state when to avoid this tool or compare directly with siblings.

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