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

There are no annotations provided, so the description must carry the burden. It says it is 'Honest' and 'flags what it cannot see,' which gives some insight into limitations, but it doesn't detail how the critique is delivered or if there are any side effects. It's a non-destructive, read-only operation implied, but this is not explicitly stated.

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 and informative. It front-loads the purpose and rubric, and then mentions the heuristics and limitation in a compact way. 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?

The tool has a clear input schema and no output schema, but the description explains that it scans 'your description' for red flags and asks questions about the real page. It covers the main steps and limitations. The complexity is moderate, and the description is sufficient for an agent to know what input to provide.

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 schema descriptions cover both parameters: 'design' and 'intent' are explained. The description adds context on how 'design' should be described (concretely: layout, type, colour, etc.), which adds value beyond the schema. But overall, the schema already covers the basics, so baseline is 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 clearly states the tool's purpose: providing a structured critique of a design using a specific rubric (Awwwards SOTD). It specifies the verb 'critique' and the resource ('design'), and the rubric details distinguish it from other tools that focus on specific aspects like principles or palettes.

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 it's for critiquing a design, but it doesn't explicitly say when to use this instead of other tools. However, the rubric and the mention of 'real page' suggest it's for evaluating an existing design, but no explicit exclusions or alternatives are named.

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 of behavioral disclosure. It transparently states the content ('laws' + 'audit plan') and implies a read-only reference behavior, but it does not describe the return format, level of detail, or what 'audit plan' entails. This is adequate for a knowledge-retrieval tool, but not rich.

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 tight sentences with zero filler. The first sentence front-loads the core content (principles list and audit plan), and the second supplies usage context and sibling differentiation. Every clause 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 simple 2-optional-parameter tool, the description covers the resource's scope and general use. However, with no output schema, it leaves the return structure ambiguous — what does 'return the 10-step audit plan' look like? The role among siblings is clear, but the exact deliverable is underspecified.

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 100%, so the baseline is 3 and the description need not compensate. The parenthetical list of principles mirrors what the schema already documents for the `topic` parameter, adding no new meaning. It does frame the values as 'permanent laws,' a slight conceptual addition, but nothing beyond schema semantics.

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 names a specific resource — permanent laws of web design, listing all eight principle IDs — plus a 10-step audit plan. It distinguishes itself from siblings by stating 'everything else in the Lemon is these rules applied to 2026,' which positions it as the foundational reference tool. It lacks a strong action verb but clearly identifies what the tool provides.

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?

'Consult for any build' gives clear when-to-use guidance, and the final sentence implies sibling tools are more specific applications of these rules. However, no explicit alternatives are named, nor are there conditions for when to prefer a sibling like lemon_palette or lemon_type_spec over this tool. The guidance is implied rather than spelled out.

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 of behavioral disclosure. 'Emit' implies an output-generating operation with no side effects, but the description does not explicitly state it is read-only, requires no permissions, or that it simply returns a spec. It does add value by indicating the output is a machine-readable format agents can apply, but omits details about the output structure or any potential 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?

The description is a single, well-structured sentence that front-loads the primary action ('Emit a complete DESIGN.md token spec') and then enumerates the included components. There is zero wasted wording, and the key distinction (machine-readable, verbatim applicability) is included without extra 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?

The tool is moderately complex (emits a full spec with six categories), and the description captures the full scope. It doesn't explain how the mood or constraint parameters affect the output, but the schema descriptions already do that. With no output schema, the description provides sufficient context for an agent to understand what it will receive, though it could mention the exact output format (e.g., Markdown or JSON) for added clarity.

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 100% coverage, meaning all parameters (mood, voice, constraint) already have descriptive names and comments. The description adds no additional meaning about these parameters or how they influence the generated spec. Since the schema fully documents them, a baseline score of 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 uses a specific verb ('Emit') and resource ('complete DESIGN.md token spec'), explicitly listing all component categories (color, radius, spacing, motion, type, layout laws). It clearly distinguishes from siblings by emphasizing 'complete' and 'machine-readable design system format,' making it obvious this is the comprehensive spec generator rather than a specialized tool like lemon_palette or lemon_type_spec.

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 is provided on when to use this tool versus the specialized siblings (lemon_palette, lemon_type_spec, etc.). The description only explains what it does, not when an agent should prefer it over alternatives. It lacks exclusions or conditions for selecting this 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?

The description adds behavioral context beyond schema: it promotes copy-paste usability, notes reduced-motion handling in every recipe, and lists specific patterns, which aids in setting expectations. However, with no annotations provided, the description carries more responsibility, but it does not disclose missing aspects like output format limits or potential errors (e.g., invalid id behavior). It is adequate but not exceptional.

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 and front-loaded with the purpose ('Copy-paste motion code recipes'), then lists specifics, and ends with the reduced-motion point. Every sentence contributes to understanding what is included, with 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?

The description is comprehensive for what it offers: it enumerates the exact recipes, mentions reduced-motion, and the param list is exhaustive. Given the moderate complexity (3 params, no output schema), the description covers the necessary context well. It could mention that omitting id returns a list, but the schema has that. It is near-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 coverage is 100%, so parameters are fully described. The description does not add much beyond the schema's parameter descriptions, but it does reinforce the search and filter capabilities implicitly. Since the schema already documents all three params, a baseline of 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 this provides copy-paste motion code recipes for specific patterns, naming the list of technologies (CSS scroll-driven, GSAP, GSAP+Lenis). It is highly specific and distinct from siblings, which focus on design principles, palettes, typography, etc. It also indicates the inclusion of reduced-motion handling, making the purpose unmistakable.

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 for developers needing ready-to-use motion code, but does not explicitly state when to use this tool versus alternatives like lemon_section_recipe (which might also include motion recipes) or lemon_trend_report. It does mention reduced-motion, but lacks explicit conditions or exclusions.

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 is the only source of behavioral disclosure. It adds valuable traits ('small, intentional', 'AA-checked'), but doesn't mention side effects, return format, determinism, or error behavior. These gaps are typical for a generation tool but the description does not fully carry the burden.

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 entire description is two short sentences, with the core action and scope in the first sentence and a crisp usage directive in the second. There's no filler or redundancy; every word contributes.

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 is simple (2 params, 1 required enum) but has no output schema and no annotations. The description indicates it returns a 'palette token set' and is AA-checked, but doesn't specify the shape of the returned tokens or any error behavior. For a low-complexity tool this is acceptable but not fully 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 coverage is 100% and both parameters already have descriptive text ('Mood voice for the palette', 'Real constraint...'). The tool description essentially restates that the palette is generated from a mood plus an optional constraint, adding little semantic value beyond the schema, so the baseline of 3 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 uses a specific verb ('Generate') with a clear resource ('palette token set'), enumerates the accepted moods, and adds a distinctive trait ('AA-checked'). The focus on palette generation clearly distinguishes it from sibling tools like lemon_type_spec or lemon_motion_recipe, which address other design aspects.

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?

It gives explicit temporal guidance with 'Use before styling anything', which tells an agent when in the workflow to call it. It doesn't name alternative tools or state when not to use it, so it lacks explicit exclusions, but the context is clear enough for a moderate score.

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 burden for behavioral disclosure. It correctly implies a read-only informational retrieval and no side effects, but it does not explicitly state safety, output format, or behavior when id is omitted. It adds minimal behavioral context beyond what the resource-oriented wording already suggests.

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 composed of two tightly written sentences that front-load the core content (award-winning sites and lessons) and then add a single, meaningful usage caveat. The example list is dense but purposeful, and there is no fluff or repetition of schema 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?

For a simple reference tool with two optional parameters, the description gives a good sense of content, but it does not describe the return shape (e.g., array of objects with site and lesson fields) or how id and rubric affect the output. Since there is no output schema, a bit more explicit return-structure context would improve completeness.

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 already provides 100% descriptive coverage for both id and rubric, so the baseline is 3. The description does not mention parameters at all, which is fine given high schema coverage, but it also does not reinforce or elaborate on parameter usage, so it stays at baseline.

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 returns a curated set of 2025-26 award-winning sites each with one stealable lesson, and the phrase 'Taste compass, not clone list' further clarifies intent. It lacks an explicit verb like 'list' or 'get', but the resource and scope are unambiguous and distinguishable from siblings like palette or type_spec.

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 the tool is used for design inspiration and taste guidance ('Taste compass'), but it does not explicitly state when to prefer this over siblings like lemon_trend_report or lemon_design_principles. No alternatives are named and no when-not conditions are provided, so usage must be inferred.

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 of behavioral disclosure. It does add value by naming three output components (structural DNA, HTML skeleton, one motion moment), but 'structural DNA' and 'award-grade' are undefined jargon, and the return format, ordering, or any side effects are not addressed.

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 one compact sentence and front-loads the three core components before the section list. 'Award-grade' is mild fluff and 'Structural DNA' is overly compressed, but there is no redundant prose or schema repetition.

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 covers six section archetypes and has no output schema or annotations, so a richer description is warranted. It never explains what 'Structural DNA' contains, what the 'ONE motion moment' means, how to combine this with lemon_motion_recipe, or what the returned content looks like.

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 schema already documents the single enum parameter with 100% coverage, so the baseline is 3. The description adds semantic value by mapping enum values to design intents (story/scrollytelling, proof/testimonials, footer/contact), which helps an agent choose the right section id. It does not add detail on omitting the parameter, but the schema already states that.

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 names the resource ('sections') and the main output components ('Structural DNA + HTML skeleton + the ONE motion moment'), so an agent can infer what the tool produces. However, it uses no explicit verb and relies on the metaphor 'Structural DNA', which weakens precision. The section list also implicitly separates it from the sibling lemon_motion_recipe, but that differentiation is not explicit.

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 is given about when to use this tool versus alternatives such as lemon_motion_recipe, lemon_design_principles, or lemon_critique. The list of section types implies it is for building those sections, but it does not state a decision rule, exclusions, or complementary 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 are provided, so the description carries full responsibility for behavioral disclosure. It implies a read-only, informational report but does not state side effects, output structure, or any constraints. The only behavioral hint is 'optionally filter by id,' which is already in the schema.

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 two concise sentences with no wasted words. It front-loads the core identity and immediately gives actionable guidance, while the optional filter is stated briefly at the end.

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 what the tool is and when to call it, but with no output schema and no annotations it leaves the return format and content details unspecified. For a simple read-only report with one optional parameter, this is adequate but not fully 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 coverage is 100% and the one parameter is already well described with examples. The description adds only 'Optionally filter to one trend by id,' which restates the schema without meaningful new semantics. 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 identifies the tool as a trend report for 2026 web design and motion, with a clear role ('Call BEFORE designing a site'). It is reasonably distinct from siblings like lemon_design_principles and lemon_motion_recipe, though it relies on the name and context rather than explicitly contrasting them.

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 gives explicit timing guidance: 'Call BEFORE designing a site.' It does not mention when not to use it or point to alternatives, but the timing instruction is clear and actionable for an agent.

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 burden of behavioral disclosure. It explains the output categories (family pairings, tokens, laws) but does not state whether the tool is read-only, what format the response takes, or any side effects. It provides moderate context about scope but not full behavioral 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 two sentences with the core purpose and outputs front-loaded. The 'Verge-DESIGN.md-style discipline' reference adds stylistic flavor but does not significantly bloat it. Efficient and well-structured.

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 one-parameter tool with no output schema, the description lists the contents of the response well enough to understand the tool's function. However, it leaves the exact response format unstated and relies on the schema for the omission behavior. Adequate but not 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?

The single voice parameter is fully documented in the schema: an enum of the five voices plus a description stating 'Omit for all + the fluid scale + laws.' The description repeats the enum values and adds no new meaning beyond the schema, so the baseline of 3 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 identifies the tool as a typography system for a voice, listing concrete outputs: family pairings, fluid clamp() scale tokens, and type laws. It is specific enough to distinguish it from color or motion tools, though it doesn't name or differentiate against siblings like lemon_design_tokens or lemon_section_recipe.

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 is given on when to use this tool versus alternatives. The voice parameter and the phrase 'Omit for all + the fluid scale + laws' imply usage, but there are no when-not conditions or routing to sibling tools, leaving the agent to infer the selection logic.

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