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

With no annotations provided, the description must fully disclose behavior. It states 'simple concatenation' and 'latest version of each component', suggesting a non-destructive read operation, but lacks details on error handling, permissions, or impact on source files. The behavioral disclosure is minimal.

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 very concise at two sentences, with the primary purpose front-loaded. It efficiently conveys the core action, but could afford slightly more detail on parameters without losing brevity.

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 presence of an output schema, return values are covered, but the description lacks parameter explanations and usage conditions. For a simple two-parameter tool, the description is still incomplete, missing guidance on parameter dependencies or error scenarios.

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 0%, so the description should compensate by explaining parameter meaning. It does not describe 'project_name' beyond implication from the purpose, and does not explain 'output_filename' at all. The default value is in the schema, but the description adds no semantic value.

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 verb (combine) and resource (HTML drafts in a project), and distinguishes itself from sibling tools by focusing on compilation rather than listing or design. However, it does not explicitly differentiate from any similar compilation tools among siblings, and the scope 'all HTML drafts' could be more precise.

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 no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as the existence of drafts, nor when not to use it. Sibling tools like list_drafts imply prior steps, but no explicit usage context is given.

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 carries full burden. It details the use of Gemini Vision, extraction of design tokens, HTML generation with TailwindCSS, JS fallback fixes, content language, and the exact return structure. It does not cover error handling or performance, but is otherwise very transparent.

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 sections, bullet points, and code blocks, front-loading the purpose. It is somewhat long due to multiple examples and detailed return type, but every part serves a purpose for an AI agent. Could be slightly more concise, but still effective.

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 complexity (10 params, no output schema, no annotations), the description is comprehensive. It covers return values in detail, modes, examples, and workflow. It implicitly differentiates from siblings by focus on reference images, but could explicitly mention alternatives. Overall, sufficiently complete.

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%, so description must compensate. It provides thorough explanations and examples for 8 of 10 parameters (e.g., image_path, instructions, context). Missing documentation for 'use_trifecta' and 'inject_js_fallbacks', but overall adds significant value 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?

The description clearly states 'Design a component based on a reference image using Gemini Vision', specifying the verb, resource, and method. It distinguishes from sibling tools like design_frontend or design_section by focusing on reference-based design, making it 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 explains two modes (extract_only true/false) and provides various examples (extract only, full design, style match for different component). However, it does not explicitly state when not to use this tool versus alternatives, such as when no reference image is available.

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 provided, the description fully discloses behavior: it uses Gemini 3 Pro, generates HTML/CSS/JS, supports various options like themes, quality levels, and multi-agent Trifecta pipeline. It does not mention rate limits or authentication, but since it is a generative tool, these are less critical. Overall, it provides sufficient 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 very long but well-structured with clear sections (Workflow, Args, Theme-Specific, Corporate Quality, Examples). It is front-loaded with the core purpose, making key information easy to find. While lengthy, the complexity of the tool justifies the verbosity.

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?

Despite the high complexity (49 parameters, no output schema, no annotations), the description covers all necessary aspects: workflow, parameter details, return fields, theme customization, quality targets, and examples. It leaves no significant gaps for an agent to understand how to use the 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?

The input schema has 49 parameters with 0% description coverage, so the description carries the full burden. It thoroughly explains each parameter's purpose, possible values, and defaults, including exhaustive lists for component_type, theme, and theme-specific options. This is essential for correct tool invocation.

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 designs frontend UI components using Gemini 3 Pro, generating production-ready HTML with TailwindCSS. It distinguishes itself from sibling tools like design_page and design_section by specifying that it creates atomic components (atoms, molecules, organisms) for assembly by Claude.

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 context on when to use the tool ('perfect for creating UI components that Claude Code can then integrate') and includes a workflow explaining its role in a larger pipeline. However, it does not explicitly state when not to use it or list alternative tools for different component sizes.

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 provided, the description carries the full burden. It discloses the use of Gemini 3 Pro, output format (HTML with TailwindCSS), and return fields including design_notes. However, it does not mention potential side effects, authorization requirements, or whether the tool is idempotent.

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 for purpose, arguments, and return value. It is appropriately sized for the tool's complexity, with no redundant 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?

Given 8 parameters, no output schema, and no annotations, the description fully covers inputs, outputs, and behavior. It explains the return dictionary with six fields, making it complete for an agent to use.

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?

The description includes a full 'Args:' section with detailed explanations, default values, and examples for all eight parameters. Since the schema has no descriptions (0% coverage), this adds significant meaning beyond the schema alone.

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 'Design a full page layout using Gemini 3 Pro' and lists nine specific template types, making the purpose unambiguous. It distinguishes from sibling tools like 'design_section' by focusing on complete pages.

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 detailed guidance on when to use the tool, including a list of template types and example configurations. However, it does not explicitly state when not to use it or mention alternative tools for specific cases, which would improve guidance.

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 fully discloses behavior: generates HTML with TailwindCSS, outputs design tokens for chaining, uses Gemini model, matches style from previous_html, configurable language, and lists return fields. It covers what the tool does and how it works.

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: purpose, usage, chain workflow, args, returns, example. It front-loads the purpose. While slightly long, every part adds value; minor redundancy in the chain example could be trimmed.

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 12 params, no output schema, and no annotations, the description is thorough. It explains the chain workflow, provides a full example, lists return fields, and covers most parameters. Missing explanation for three boolean params prevents a perfect score.

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 0%, but the description provides extensive details for most parameters: section_type options with descriptions, context example, previous_html usage, design_tokens format, content_structure example, vibe options, content_language codes. Three boolean params (auto_fix, use_trifecta, inject_js_fallbacks) are not explained, leaving a small gap.

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 'Design a single page section that matches previous sections' and explains the chain workflow for building pages section-by-section. This differentiates it from siblings like 'design_page' (whole page) or 'design_from_reference'.

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 says 'Use this tool to build large pages section-by-section' and provides a detailed step-by-step chaining workflow with an example. It implies not to use for entire page design, and the chain example shows how to combine sections.

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 must fully disclose behavior. It mentions model names but omits critical traits like authentication, cost implications, rate limits, or whether generation is synchronous. The agent lacks insight into side effects or prerequisites.

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, with the main purpose front-loaded and an organized Args list. However, the parameter descriptions are terse, sacrificing depth for brevity. The structure is efficient but could benefit from additional context.

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 7 parameters, no output schema, and no annotations, the description is incomplete. It does not explain return format, side effects, or constraints like image limits. The agent cannot fully anticipate tool behavior, especially regarding output handling for base64 vs file.

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%, so the description must compensate. However, parameter explanations are minimal (e.g., 'Image ratio' for aspect_ratio), offering little beyond schema titles. For example, 'model' lacks valid values, and 'output_format' doesn't clarify outcomes (base64 vs file path). This fails to resolve ambiguity for the agent.

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 verb 'Generate' and the resource 'design assets', implying image generation. It distinguishes from sibling tools like design_from_reference by specifying use of Gemini or Imagen models, making the 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 no guidance on when to use this tool versus alternatives like design_from_reference or refine_frontend. It lacks context for selection, such as scenarios where image generation is appropriate vs. other design tasks.

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 the description carries full burden. It indicates a read-only operation but doesn't explicitly state non-destructive behavior or permissions needed. Basic transparency is present.

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 two sentences plus a concise parameter documentation, front-loaded with the primary purpose. 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 no output schema, the description adequately covers purpose and parameter, but could hint at return format (e.g., list of draft names). Still sufficient for a simple listing 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 coverage is 0%, but the description adds meaning by explaining that project_name is a folder in temp_designs, providing context beyond the schema's type and default.

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 verb ('List'), the resource ('saved design drafts'), and the scope ('for a given project'), effectively distinguishing it from siblings like compile_project_drafts and design_frontend.

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 usage context ('recover lost work or see previous versions') but does not explicitly mention when not to use or alternative 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 exist, so the description bears full responsibility. It fully discloses the return structure (dictionary with fields like components, themes, etc.) and notes new features (theme_factories). It does not mention side effects or permissions, which are minimal for a read-only listing.

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 front-loaded with the main action and resource, followed by a clear bulleted list of return fields. It is slightly verbose but well-structured and every sentence adds value. Could be trimmed slightly, but overall effective.

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 no parameters and no output schema, the description is comprehensively covers the return values and structure. It lists all eight fields with brief explanations, making the tool's behavior fully predictable.

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?

There are zero parameters, and the input schema is empty. Per guidelines, baseline is 4. No additional parameter information is needed, and the description does not attempt to add param details beyond what the schema provides.

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 explicitly states 'List available frontend design options' with a specific verb and resource. It includes detailed contents like component types, themes, templates, and mentions 'NEW: advanced theme factory options,' clearly distinguishing it from sibling tools that involve design actions or other listings.

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 explicit guidance on when to use this tool versus alternatives. The purpose is clear enough that an agent can infer it should be used to retrieve design options before crafting a design, but there is no statement of prerequisites or exclusionary conditions.

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 are provided, so the description carries full burden. It describes a simple read operation ('List', 'Returns information') with no destructive hints. The return type is given ('Dict containing image models with their specifications'). No hidden behaviors are implied.

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 (three sentences), front-loaded with purpose, and every sentence adds value: purpose, context, return type. No 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 simplicity (no parameters, no output schema), the description adequately explains what it does and what it returns. It doesn't detail the exact structure of the dict, but for a listing tool, this is sufficient.

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?

The tool has zero parameters, so input schema coverage is 100%. The description adds no parameter details, which is appropriate as there are none. Baseline score of 4 applies.

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 action ('List') and the resource ('available Gemini models for design tasks'). It also distinguishes from sibling tools by specifying that this is a listing tool for models, while siblings involve design generation, compiling drafts, etc.

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 context on when to use the tool ('design-focused', 'use image models for creating design assets'). It implies this is for browsing models before generating, though it doesn't explicitly state when not to use it. Clear enough for 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?

No annotations provided; description discloses the tool aborts sessions, returns a dict with success and message, and that sessions auto-expire. Could mention more about side effects, but sufficient for a simple operation.

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 Args, Returns, and Example sections. Slightly verbose but clear and 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?

Covers purpose, usage, parameter, return value, and example thoroughly for a simple tool. No gaps given the tool's complexity.

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 0%, so description compensates by defining 'session_id: Session ID to abort' and showing usage in an example. Adds value beyond schema's minimal title.

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 states 'Abort and cleanup a MAESTRO session' with a specific verb and resource, clearly distinguishing it from sibling tools like 'maestro_start_session' or 'maestro_answer'.

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 says to use for canceling an in-progress interview and freeing resources, and mentions automatic expiration after 1 hour. Lacks explicit exclusions or alternatives, but context is clear.

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 are absent, so the description carries full burden. It explains the return structure (next question or final decision) but does not disclose side effects, state changes, or whether the tool is idempotent. It does not mention prerequisites beyond having a valid session_id. While the output behavior is clear, the behavioral traits beyond output are not fully transparent.

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 sections for Args, Returns, and Example. It is front-loaded with the purpose. However, it is somewhat verbose; the Returns section could be more concise. Overall, it is organized and readable.

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 (interview flow with two possible outcomes) and no output schema, the description provides a thorough Returns section explaining both cases. It covers parameters and usage context. Minor omission: no mention of error handling or invalid session/ID 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?

With 0% schema description coverage, the description effectively adds meaning. It documents all four parameters in the Args section, explaining where to obtain each (e.g., session_id from 'maestro_start_session', question_id from 'question.id'). It also includes an example and notes about 'selected_options' typically requiring exactly one. This compensates well for the schema gap.

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 purpose: 'Submit an answer to the current MAESTRO question.' It identifies the verb ('submit') and resource ('MAESTRO question'), and explains its role in the interview flow. However, it does not explicitly differentiate it from sibling tools like 'maestro_get_decision' or 'maestro_get_progress', which reduces clarity slightly.

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 says 'Call this tool to answer each question during the MAESTRO interview.' It provides an example and explains two possible outcomes. However, it does not specify when NOT to use the tool (e.g., after interview is complete) or mention alternative tools from the sibling list. This leaves room for ambiguity in choosing the correct tool.

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?

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It explains the execution process, the multi-agent Trifecta pipeline for higher quality, and the return values including status and design notes. It does not mention error handling beyond 'status: failed' or potential side effects, but overall provides adequate 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 a clear purpose statement, separated Args and Returns sections, and an example. Every sentence contributes value, and the information is front-loaded. The length is appropriate for the complexity of the tool.

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 (three parameters, no output schema, multiple siblings), the description covers prerequisites, parameter options, return values, and includes an example. It lacks details on error conditions beyond 'failed' status and does not explain behavior when the session is not ready, but overall is sufficiently complete for an agent to invoke correctly.

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?

The input schema has 0% description coverage, so the description must compensate. It does so comprehensively: session_id is described as 'Active session ID with a decision ready', use_trifecta explains the multi-agent pipeline, and quality_target provides explicit options with threshold and iteration details. This adds substantial meaning beyond the schema titles.

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 executes a MAESTRO session decision to generate design output (HTML, CSS, JS). It is distinct from sibling tools like maestro_get_decision (which retrieves the decision) and design_frontend (which may create standalone designs).

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 explicitly requires a decided session before use, mentioning both 'completing the interview' and 'calling maestro_get_decision' as prerequisites. It also details the quality_target options and their implications. However, it does not provide explicit guidance on when not to use this tool or compare it to alternative design tools among siblings.

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 describes return structure and example usage, implying a read-only analytics operation. However, it does not explicitly state that data is not modified or mention rate limits or permissions.

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 three paragraphs with an example including Turkish text, making it longer than needed. The example is somewhat verbose and could be condensed for an English-speaking agent.

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 return data categories and provides an example. Lacks prerequisites (e.g., needing an active session) and does not mention any error conditions, but overall adequate for a simple analytics 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?

Input schema has zero parameters (100% coverage trivially). Description adds value by explaining the output fields and context, which is sufficient for a parameterless tool.

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 'Get MAESTRO session analytics and usage metrics,' listing specific categories (session tracking, cost analysis, quality metrics). Distinguishes from sibling tools like maestro_abort or maestro_start_session.

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 explicit guidance on when to use this tool versus alternatives. The only contextual hint is 'Phase 6 feature,' but it lacks when/why not or alternative tool references.

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 are provided, so the description must fully disclose behavior. It explains the tool forces a decision and skips questions, but does not mention side effects (e.g., whether the session becomes unusable or if the decision is irreversible). The return format is detailed, but the behavioral impact is partially unclear.

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 Args, Returns, and Example sections, making it easy to scan. The purpose is front-loaded. Could be slightly more concise, but the structure compensates.

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 tool with one parameter and no output schema, the description provides detailed return structure and usage example. It covers purpose, input, output, and condition for use. However, it omits potential error cases or prerequisites.

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?

The single parameter 'session_id' is described as 'Active session ID from maestro_start_session', which adds meaningful context beyond the schema's bare 'Session Id'. This helps the agent understand the parameter's origin and validity requirements.

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 the tool forces a design decision using current answers and skips remaining questions. The verb 'force' combined with 'skip remaining questions' precisely defines the tool's unique action, distinguishing it from siblings like maestro_answer or maestro_abort.

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 states 'Use this tool when you want to proceed with partial information and skip the remaining interview questions.' This provides clear context but does not explicitly mention when not to use it or list alternative tools, though the sibling names hint at 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?

No annotations exist, so the description carries the full burden. It details the return structure (progress bar, percentage, current_step, total_steps, category_tip) and gives an example. However, it does not explicitly state that the operation is read-only or discuss side effects, which would raise transparency further.

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 headings (Args, Returns, Example) and is concise. Every sentence adds value; there is no redundancy or fluff. The example further enhances clarity without unnecessary length.

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?

Despite no output schema and no annotations, the description fully covers the tool's purpose, parameters, return values, and provides an example. For a simple retrieval tool with one parameter, this is complete and demonstrates strong contextual coverage.

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?

The input schema has 0% description coverage for the single parameter 'session_id'. The description adds 'Active session ID' which provides basic semantics but does not elaborate on format or constraints. The baseline of 3 is appropriate given the low coverage and minimal compensation.

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 uses a specific verb 'Get' and clearly identifies the resource 'rich formatted progress display for a session'. It distinguishes itself from sibling tools like 'maestro_get_decision' and 'maestro_get_analytics' by focusing on progress tracking.

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 'Phase 6 feature' hinting at context but does not explicitly state when to use this tool over alternatives. No when-not-to-use or alternative suggestions are provided, leaving usage largely implied.

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 are provided, so the description carries full burden. It describes that the tool uses an AI engine and returns recommendations, but it does not disclose whether it is read-only, requires authentication, or any other behavioral traits. It is not contradictory but lacks depth.

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 fairly concise with a front-loaded purpose statement. It includes a brief explanation of the engine, return fields, and an example. However, the example includes non-English text, which may slightly reduce clarity.

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 no parameters and no output schema, the description covers the tool's purpose, how it works, and the return structure with an example. It is largely complete, though it could mention error handling or prerequisites.

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?

The input schema has zero parameters, and schema coverage is 100%. Per calibration, baseline is 4. The description adds value by explaining the return structure and example, which compensates for the lack of parameters.

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 states the tool gets smart design recommendations based on user preferences, specifying the resource (recommendations) and the verb (get). It mentions factors like user preference history and project context, but does not explicitly differentiate from sibling tools like maestro_get_decision or maestro_get_analytics.

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 implies usage context with the example 'Get recommendations before starting a session', but it does not provide explicit when-to-use or when-not-to-use guidance, nor does it compare with 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 carries the full burden. It details the interactive flow, v2 soul extraction feature, and return fields. It does not mention rate limits or resource usage, but the level of detail is sufficient for safe invocation.

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 fairly lengthy but well-structured with summary, explanation, Args, Returns, and Example sections. It is front-loaded with the main purpose, and each sentence adds value. Minor redundancy could be trimmed.

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, the description includes a comprehensive Returns section with all fields. It explains the tool's role among 19 siblings, mentions v2 features, and provides an example that shows session flow. Complete for a session-starting 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?

Despite 0% schema description coverage, the description provides detailed explanations for all three parameters in a dedicated Args section, including examples and effect on behavior (e.g., design_brief triggers v2). This compensates well for the sparse 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 the tool starts a new MAESTRO design wizard session, serving as the entry point for the guided design workflow. It uses specific verbs like 'Start' and distinguishes its role from sibling tools like maestro_answer and maestro_abort.

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 explains that this is the entry point, and provides context for when to provide design_brief or existing_html, and mentions that MAESTRO may suggest alternative modes. It does not explicitly state when not to use it but the example shows the next step (maestro_answer).

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 provided, the description carries the full burden. It discloses that all content is generated in Turkish, that the model is always gemini-3-pro-preview, and expects previous HTML. However, it does not discuss potential side effects or limitations, such as what happens if the input HTML is invalid.

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 a clear intent, usage guidance, parameter descriptions with examples, and return value details. Every section is valuable and there is no wasted text.

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 has 6 parameters (2 required) and no output schema, the description covers core functionality well, including return fields. However, missing documentation on three boolean parameters (auto_fix, use_trifecta, inject_js_fallbacks) prevents a perfect score.

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 0% per context signals. The description adds meaning for three parameters (previous_html, modifications, project_context) with examples, but three parameters (auto_fix, use_trifecta, inject_js_fallbacks) are undocumented. This partial coverage warrants a score of 3.

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 uses the verb 'Refine' and specifies the resource as 'an existing component design based on feedback.' This clearly states the tool's purpose and differentiates it from sibling tools like design_frontend which create new designs.

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 states 'Use this tool to iterate on a design without starting from scratch,' providing clear guidance on when to use it. It implies that for new designs, other tools like design_frontend should be used.

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 explains that only the target section is replaced, others preserved, and that visual consistency is maintained. Also describes return format and 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-structured with clear sections: intro, critical note, args, returns, example. Each sentence adds value, and the length is appropriate for the tool's complexity.

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 7 parameters (3 required), no output schema, and no annotations, the description covers input requirements, behavior, return format, and provides an example. It is very complete for the tool's purpose.

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 0% (no parameter descriptions in schema). The description adds detailed explanations for each parameter, including valid section types, examples for modifications, default values for preserve_design_tokens and content_language, and even describes the return value structure.

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 replaces a single section in an existing page with an improved version, distinguishing it from sibling tools like design_section or refine_frontend by specifying it works on existing page HTML with section markers.

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 critical usage notes (section marker format), valid section types, and an example. It implies iterative design improvement but could explicitly state when not to use this tool versus alternatives like design_page or compile_project_drafts.

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 are provided, so the description must convey behavioral traits. It only states 'Initialize a new design project folder,' but does not disclose side effects (e.g., whether it overwrites existing projects), required permissions, or any limitations. This is insufficient for a creation action.

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 very concise, consisting of one line and an args section. It is front-loaded and avoids unnecessary detail. However, it could be slightly improved by integrating the args info more naturally, but overall it is appropriately sized.

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?

Despite the tool having an output schema (not detailed but present), the description does not explain return values or what happens after initialization. It lacks information on behavior if the project name already exists, where files are stored, or how to verify success. For a project initialization tool, this is incomplete.

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?

The single parameter 'project_name' has no schema description (0% coverage). The description adds an example ('e.g. 'burger_landing''), which provides some context but does not specify naming conventions, uniqueness constraints, or accepted formats. It adds marginal value over the parameter name alone.

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 purpose: 'Initialize a new design project folder.' The verb 'initialize' and the resource 'project folder' are specific. This distinguishes it from siblings like 'compile_project_drafts' or 'design_from_reference', which serve different functions.

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 no guidance on when to use this tool versus alternatives, no prerequisites, and no conditions for appropriate usage. It simply states what it does, leaving the agent without context for decision-making.

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 fully conveys behavior: it returns a dict with passes, ratio, required_ratio, message, and recommendations. It also specifies hex format requirement.

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 structured with Args and Returns sections and includes an example, but it is slightly long. Still, 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?

Despite no output schema, the description details the return dictionary. The example further clarifies usage. Everything needed for a validation tool is present.

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 0%, so the description compensates fully by explaining each parameter: foreground/background hex format, wcag_level options, and text_size with size 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 validates color contrast ratio for WCAG compliance. This distinguishes it from sibling tools which are design or project management related.

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 explains to use this tool before using color combinations in designs. It provides good context but does not explicitly mention when not to use or alternatives.

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