envious-canvas

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

Annotations already indicate non-readOnly (false), non-destructive, and open-world. The description adds critical post-processing behavior: always open generated images in Preview. However, it lacks details on cost implications or additional side effects, which would further enhance transparency.

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 well-structured with clear sections: intro, usage guidance, exclusion list, important note, and examples. Every sentence serves a purpose, and it is front-loaded with the core function. Highly concise with zero waste.

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 the tool's complexity, the description covers modes, usage, and post-processing. The output schema exists, so return values are covered. However, it omits mention of the spend_authorization parameter and potential cost implications, which are relevant for an image generation tool.

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 description coverage is 0%, but the schema itself has rich property descriptions. The tool description compensates by explaining the plan-based vs direct usage distinction via examples, adding meaning beyond the schema. Yet it does not describe all parameters individually, though the schema covers them.

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's function: generating marketing images with two modes (plan-based or direct). It explicitly distinguishes from sibling tools by listing what not to use (canvas_render_layout, canvas_edit_image, canvas_inspect_asset), making its purpose unambiguous.

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 explicit guidance on when to use each mode (plan-based for complex jobs, direct for quick one-shot) and when not to use the tool, with references to alternative sibling tools. This fully informs the agent on appropriate 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?

Description details all actions and includes an important note about opening output in Preview. Annotations indicate mutation but no contradiction. Could mention side effects or error handling.

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?

Well-organized with clear sections, bulleted actions, and a concrete example. No wasted words, front-loaded purpose.

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, usage, actions, and a follow-up step. Output schema exists so return values are covered. Could include prerequisites or error states.

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 has per-parameter descriptions, but description adds value by listing actions with context (e.g., prompt required for edit) and providing an example.

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 modifies/enhances/transforms existing images, lists four specific actions, and distinguishes from siblings like canvas_create_image and canvas_render_layout.

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 'Use when' and 'Do not use when' sections with named alternatives (canvas_create_image, canvas_render_layout).

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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds context about the types of analysis. No contradictions; description complements annotations.

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?

Concise: three sentences plus use-case guidelines and an example. No wasted words; front-loaded with purpose.

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 annotations (read-only, nondestructive) and an output schema, the description covers purpose, usage guidance, and parameter hints adequately for a focused analysis tool.

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?

Description provides semantic meaning for parameters via example and mentions structured attribute extraction. Schema descriptions are detailed, but the tool description adds usage context beyond the 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?

Description clearly states 'Analyze an image using AI vision' with specific actions (describe, extract, QA check). Distinguishes from sibling tools like canvas_create_image and canvas_edit_image.

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 provides 'Use when' and 'Do not use when' sections, guiding the agent on appropriate contexts and alternatives. Includes a concrete example.

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?

Annotations set destructiveHint=false, but the description lists 'delete' as a valid action for brand kits and generated assets, which contradicts the non-destructive hint. This is a direct contradiction, so score is 1 per rules.

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?

Description is well-structured with sections, lists, and an example. It is concise with no filler, front-loads the purpose, and every sentence adds value.

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 the tool's complexity (multiple targets, actions, many parameters) and no output schema, the description covers usage guidelines and examples well. It lacks details on return values but is sufficient for an agent to understand core behavior.

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?

Description includes an example and lists actions, but does not explain each parameter's role. Schema description coverage is stated as 0% (though schema actually has descriptions), so the description fails to fully compensate. However, the example provides some context, making it adequate but not exceptional.

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?

Description specifies verb and resource: 'Create, list, search, and inspect brand kits and generated assets.' It clearly distinguishes from siblings by stating 'Do not use when: The user wants to generate or edit images.' Sibling tools include image creation/editing, so this differentiation is effective.

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 'Use when' and 'Do not use when' sections, plus lists of supported actions per target. This gives clear context for when to invoke this tool vs alternatives, fulfilling the guideline requirement exceptionally.

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?

The description explains the two actions (plan and approve) and mentions that planning returns a CreativePlan with plan_id and status. It also notes that planning is a prerequisite for generation. While annotations already indicate the tool is not read-only and not destructive, the description adds context about the multi-step workflow. It does not fully detail side effects or rate limits, but it is sufficient for the tool's purpose.

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 concise, well-organized, and front-loads the main purpose. It uses bullet points for use/not-use, a numbered list for actions, and an example. Every sentence adds value with no redundancy or extraneous information.

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 description covers the dual-mode operation and gives a concrete example, which is sufficient for most users. It mentions the return of a CreativePlan but lacks details on the output structure (no output schema in the tool definition). Additional context on error handling or edge cases would improve completeness, but the description is reasonably complete for a planning tool.

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?

Context signals indicate schema description coverage is 0%, requiring the description to compensate. The description provides a usage example that illustrates key parameters (goal, subject_type, reference_image) and their roles, but does not explain all 15+ parameters. The schema itself contains descriptions for each parameter, which offsets some of the burden, but the description could be more thorough in explaining parameter interactions.

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 that the tool is for planning and validating creative requests before generation. It explicitly distinguishes from siblings by listing use and do-not-use cases, such as using canvas_create_image for quick one-shot generation, and names alternative tools. The verb 'Plan and validate' is specific and the resource 'creative request' is well-defined.

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 includes a dedicated 'Use when' section specifying when to preview costs, workflow, and fidelity, and a 'Do not use when' section with explicit alternatives (canvas_create_image, canvas_render_layout, etc.). This provides clear, actionable guidance for tool selection.

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?

Beyond annotations (idempotentHint=true), the description labels it as a deterministic renderer (not AI generation) and adds a mandatory post-invocation instruction to open the image in Preview, which is valuable behavioral guidance.

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?

Well-structured with clear sections, concise sentences, and no redundancy. Every sentence adds value, and the important post-invocation note is highlighted.

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 the parameter complexity and presence of an output schema, the description covers when to use, an example, and a critical post-invocation step. Lacks error handling info, but the output schema fills return value gaps.

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?

Despite 0% schema description coverage, the schema itself has detailed property descriptions. The description adds a usage example that illustrates typical parameter combinations but does not systematically explain each parameter, so baseline 3 is appropriate.

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 HTML/CSS to pixel-perfect images, uses a specific verb ('Render'), and distinguishes itself from AI-generation tools by naming the sibling tool canvas_create_image for those cases.

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?

Explicit 'Use when' and 'Do not use when' sections, with direct reference to canvas_create_image for AI-generated imagery. Provides clear context and exclusion criteria.

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