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

With no annotations, the description carries the behavioral burden. It does disclose an important trait: the tool does not just audit, it automatically self-heals contrast and ARIA failures. But it leaves unclear what changes are made, whether the input AST is mutated in place, whether the operation is reversible, and what happens when no failures are found.

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?

One compact sentence delivers the core action, the target resource, the issue categories, and the healing behavior. There is no filler 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?

The input side is well covered because the only parameter is fully documented in the schema. However, with no annotations and no output schema, the description omits what the tool returns and what exactly 'self-heal' modifies, which are meaningful gaps for an agent deciding whether the call succeeded or what side effects occurred.

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 is fully described in the schema as 'The component AST to audit and heal,' and the tool description does not add meaning beyond that. With 100% schema coverage, 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 names a specific verb (audits) and resource (component), and specifies the scope: accessibility and structural issues, plus automatic healing of contrast or ARIA failures. This clearly separates it from sibling tools like generate, mutate, export, and figma_sync.

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 purpose strongly implies when to use it: after producing or receiving a component that needs accessibility/structural verification and repair. However, it does not explicitly state when not to use it or name alternatives, so guidance is implied rather than explicit.

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 the full burden of explaining behavior. It does not state whether the export is a pure read/conversion that returns code, whether it writes files, or whether it modifies the component AST. This is a meaningful gap for an agent choosing and invoking the tool.

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

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

A single, front-loaded sentence states the action and scope without filler. Every part earns its place, and the most decision-relevant information appears immediately.

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?

With no output schema and no annotations, the description should explain what the tool returns or produces. It does not. It also says little about the component AST structure beyond what the schema already states. This leaves the agent uncertain about the expected result of invoking 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 schema already documents both parameters with 100% coverage, so the baseline is 3. The description adds useful semantic detail beyond the schema by specifying 'idiomatic', 'React + Tailwind', 'Svelte 5 (Runes)', 'Vue 3', and 'standalone Custom Web Element', which clarifies what each target enum value practically maps to.

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 and resource: 'Exports a component' to a defined set of output targets. It clearly distinguishes this from sibling tools like producer_generate_component or producer_mutate_component by focusing on export/conversion rather than generation or mutation.

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 intended use is implied: use this when you need to convert a component AST into framework-specific code. However, the description gives no explicit guidance on when not to use it or how it relates to alternatives such as producer_generate_component or producer_mutate_component.

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 the full burden of disclosing behavior. It only restates the import/export direction and gives no information about side effects, overwrite behavior, authentication needs, or whether the operation is a read or write.

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?

A single, front-loaded sentence with no filler. It communicates the core purpose immediately and every word 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?

Adequate for a two-parameter tool with a fully documented schema, but with no annotations and no output schema, it omits behavioral and return-value details an agent might need to fully understand the consequences of a sync operation.

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%, and the schema already documents the 'action' enum and 'tokens' object. The description adds no additional parameter-level meaning, but the schema fully covers the 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?

States a specific verb ('Imports or exports') and resource ('Tokens Studio / Figma design token trees'), making the tool's role unambiguous and distinct from the sibling generate, mutate, and export tools.

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 clear context for when to use the tool: synchronizing Tokens Studio/Figma design token trees. However, it does not explicitly name sibling alternatives or state when not to use them.

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 the full behavioral burden. It communicates a transformation but does not disclose whether the operation is read-only, whether it validates the input DSL, what happens on invalid input, or whether there are side effects like persisting or overwriting data.

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 with no filler. The action and object are front-loaded, and every word contributes to explaining the input and output.

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 high-level input and output, but it does not explain how to construct a valid compactSpec in Producer Cue DSL, what the AST structure looks like, or what errors or side effects to expect. For a one-parameter tool with no annotations and no output schema, this is just barely adequate.

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% and the compactSpec parameter already references Producer Cue DSL, so the baseline is 3. The tool description adds the 'high-density' qualifier and the AST output context, but no extra syntax, subfield requirements, or examples 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 uses a specific verb, 'Expands', with a specific resource, 'Compact Component specification', and names the concrete output: 'full, standards-compliant Component AST.' This clearly differentiates it from siblings like producer_generate_theme or producer_mutate_component.

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 input trigger is implied: use this tool when you have a Compact Component specification that needs expansion into a full AST. However, it never explicitly states when not to use it or compares against alternative tools, so the agent must infer routing from the description alone.

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 the burden of behavioral disclosure. It does disclose a key behavioral trait: the output is WCAG AA-compliant and includes 10-step tonal palettes, which implies the tool performs color computation and contrast checking. However, it doesn't disclose whether the tool validates inputs, what happens on failure, whether it mutates any state, or whether it is idempotent. For a generation tool, this is adequate 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?

The description is a single, well-structured sentence that front-loads the core purpose (generates an accessible theme) and includes the key differentiator (WCAG AA, 10-step palettes). Every word earns its place, and there is no redundancy or filler.

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 generation tool with 4 parameters and no output schema, the description is reasonably complete: it states the output type and key quality attributes. However, it doesn't mention what the generated theme contains beyond palettes (e.g., typography, spacing, component tokens), nor does it explain the relationship between the seeds and the output. An agent might not know what to expect in the return value, but the core calling context is covered.

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 schema already documents all four parameters. The description adds the context that the primarySeed is a brand hex color and that the output is a 10-step palette, which helps understand how the seed is used. However, it doesn't add details about the scheme parameter's effect or the neutralSeed's role beyond what the schema says. 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's function: generating an accessible, WCAG AA-compliant design system theme with 10-step tonal palettes. It specifies the verb (generates), the resource (design system theme), and a key differentiator (accessibility compliance, 10-step palettes). It doesn't explicitly distinguish it from siblings, but the resource and output are distinct enough from component generation, mutation, auditing, export, primitives, and Figma sync.

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 for creating themes, but it doesn't explicitly state when to use it versus alternatives like producer_generate_component or producer_get_primitive. There is no mention of when not to use it or what prerequisites exist (e.g., needing a seed color). The context is clear enough for a straightforward generation task, but no explicit routing guidance is provided.

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 discloses that the primitive is headless, accessible, and production-ready, which adds value. However, it does not describe what the tool returns (e.g., code, component object) or any side effects, leaving behavioral transparency incomplete for a getter 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?

The description is a single concise sentence that front-loads the core action and resource, then lists the accepted types in parentheses. Every word contributes to clarity, with no redundancy or 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?

Given the simple tool with one enum parameter and no output schema, the description is mostly complete but omits the return format or expected output. An agent might know what to pass but not what to expect back, creating ambiguity for downstream 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?

Schema coverage is 100% with the single 'type' parameter fully enumerated. The description adds no additional parameter details beyond the schema's enum and description, so it meets the baseline without enhancing understanding.

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 retrieves a 'production-ready, accessible headless UI primitive' and lists the specific types. The verb 'retrieves' distinguishes it from sibling tools that generate, mutate, or audit components/themes, making the purpose unambiguous and well-differentiated.

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 retrieving a primitive but does not explicitly mention when to use it versus alternatives like producer_generate_component or producer_generate_theme. No exclusions or alternative guidance is provided, so the agent must infer context from the tool name and sibling list.

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 indicates that the tool mutates an existing component and avoids regenerating it, but it does not explain whether changes are persisted, reversible, atomic, or what the return value is. For a mutation tool this is a meaningful gap.

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, front-loaded sentence with no wasted words. It conveys the action, target, scope, and key differentiator in under fifteen words, which is ideal for quick agent comprehension.

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 no annotations and no output schema, so the description should compensate by explaining observable behavior and expected return. It does not mention what the tool returns, whether the input component is mutated in place, or what happens on failure. Given the tool's mutating nature and nested object parameters, 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?

Schema description coverage is 100%, so the input schema already documents both required parameters. The description adds a useful shorthand by listing mutation scopes ('style, text, variants, children') that map to the mutations array, but it does not add substantial semantic detail 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 uses a specific verb ('Applies surgical mutations') and a clear resource ('existing component'), and explicitly contrasts itself with full regeneration, distinguishing it from sibling tools like producer_generate_component. It also lists the mutation categories, making its 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 clearly communicates that this tool is for targeted edits to an existing component rather than full regeneration. It does not explicitly name alternatives or state when-not-to-use, but the contrast with regeneration provides sufficient contextual guidance.

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