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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description adds value by disclosing the exact returned artifacts and a hard behavioral rule ('Never rewrite a component from its summary'). It does not discuss volume, latency, or what happens when a requested component is not found, which keeps it below a 5.

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

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

Three sentences, front-loaded with the returned payload, then when to call it, then the input mode and the key constraint. No filler or restated title.

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, the description compensates by enumerating what comes back, and it supplies the workflow ordering an agent needs. The remaining gap is edge behavior — multiple components in one call, missing components, and how project_context affects results — none of which is stated.

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%, including the components/requirements derivation rule, so the schema carries the parameter burden. The description's 'component names or a requirements brief' only restates that contract without adding syntax or format detail, which is the baseline-3 case.

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 (Return) and an enumerated resource payload: source, copy target, dependencies, adaptation notes, replacement guidance and feedback questions for one or more components. This 'copy-ready bundle' framing is clearly distinct from the summary-oriented siblings list_components and get_component_details, so an agent can pick it without opening a schema.

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?

Gives explicit sequencing — 'Use this after asking for requirements and before writing or editing code' — and states the required input mode ('Provide component names or a requirements brief'). It stops short of naming alternatives or a when-not condition (e.g. use get_component_details when you only need metadata), so it is clear context rather than full routing.

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

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds context the annotations cannot: the full shape of the returned content (props, variants, dependencies, examples, source code) and the fact that the response is markdown containing a copy target and install instructions. It also discloses a scope trait — both local and marketplace catalogue records are supported.

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

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

Two sentences, no filler. The payload enumeration comes first, followed by the markdown/install note and the local-vs-marketplace scope. Every clause contributes information an agent would otherwise lack.

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, the description carries the return-value burden and does so by naming the content categories and the markdown/install framing. Combined with annotations covering the safety profile and a fully documented single parameter, nothing an agent needs to invoke this correctly is missing.

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 single parameter's description already enumerates the accepted identifier forms (name, slug, export name, file, import path, catalogue author/slug, record id). The description adds nothing beyond that, 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 gives a precise verb ('Return one component's') and then enumerates the exact payload: metadata, parsed props, CVA variants, dependencies, usage examples, guidelines, related components and source code. That is far more specific than a bare 'get details'. It does not, however, differentiate itself from the sibling get_component_bundle, which an agent could plausibly confuse with a single-component lookup.

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?

Usage is only implied: an agent infers it should call this when it needs details for one named component, versus list_components for enumeration. There is no explicit when-to-use, no exclusion or prerequisite, and no mention of when get_component_bundle or get_design_tokens would be the better choice.

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

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

Annotations already declare this as a read-only, idempotent, non-destructive, closed-world operation, so the safety profile is fully covered. The description adds value beyond that by disclosing what the payload contains — CSS variables, guidance, and contrast pairs — which matters because there is no output schema. It stops short of describing size or structure of the response.

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 sentence that front-loads the verb and enumerates the token families with zero preamble. The enumeration is slightly list-like but every item maps to a real return category, so nothing is wasted.

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?

This is a simple, parameter-light read tool whose safety profile is fully covered by annotations and whose only input is fully covered by the schema. The description compensates for the missing output schema by naming the returned artifacts (CSS variables, guidance, contrast pairs). Only the shape and size of the response remain unspecified, which is a minor gap.

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 single parameter has an enumerated list, so the schema fully documents the token_type selector. The description restates the same token families as its content list but adds no filtering syntax or format guidance beyond what the schema provides, making 3 the correct 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 gives a clear verb ('Expose') and a concrete resource ('semantic colours, typography, spacing, radius, shadows and animation tokens'), so the agent immediately knows what comes back. It does not explicitly differentiate itself from siblings, though the sibling names (list_components, get_component_details, etc.) are component-oriented rather than token-oriented, making the distinction largely inferable.

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?

Usage is only implied: an agent can infer this is the tool to call when it needs design token values. There is no explicit 'use this when…', no statement of prerequisites, and no routing away from alternatives. The default-to-all behavior is only stated in the schema, not in the description.

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

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the description only needs to add context beyond that. It does so by disclosing that results are summaries rather than source, listing the returned metadata fields, and routing the agent to other tools for full source. It does not mention pagination behavior or how the 8,157 marketplace records are paged, but the core behavioral limitation is clearly surfaced.

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 efficient sentences with no waste. It front-loads the scope and returned fields, then adds filters and the critical summaries-only caveat in a logical order.

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, the description compensates by naming the returned metadata fields and clarifying that results are summaries only. Combined with annotations covering safety and the schema covering filter syntax, an agent has enough information to invoke the tool 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?

Schema description coverage is 100%, so the input schema already documents all four parameters, including the enum meaning for catalogue mode and the limit default. The description adds a high-level filter summary but little parameter-specific meaning beyond what the schema provides. The baseline of 3 is appropriate when the schema carries parameter 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 states a specific verb and resource: listing UI components, with precise scope covering verified local components and all 8,157 marketplace catalogue records. It also differentiates from siblings by explaining that results are summaries and that get_component_bundle or get_component_details must be called for source code, so an agent can tell these apart without opening schemas.

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 explicitly says to filter by category, query or kind, and names the alternative tools to use when copy-ready source is needed. The condition for switching tools is clear: get_component_bundle or get_component_details should be called before writing code. No relevant when-to-use guidance is missing.

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

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that: it discloses the full output composition and a concrete workflow rule ('Copy the source blocks before editing; do not regenerate them'), which tells the agent how to treat the returned source.

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

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

Two sentences, front-loaded with the purpose and then the operator instruction. The artifact list is dense but every item earns its place by telling the agent what comes back.

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

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

No output schema exists, so the description appropriately enumerates the return contents in lieu of one. Combined with annotations covering the safety profile and 100% schema coverage on parameters, an agent has nearly everything needed to call it correctly; only sibling routing is absent.

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 use_case, constraints and surface_type are all already documented in the schema. The description adds no syntax, format or defaulting detail beyond what the schema provides, so the baseline 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?

States a specific transformation (use case -> design direction) and enumerates the concrete artifacts produced: palette, type pairing, wireframe, TSX scaffold, component source. That is far more than a restatement of the title. It does not, however, explicitly differentiate itself from siblings like get_design_tokens or validate_ui_composition.

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 conveys the input-to-output story but never says when to reach for this tool versus the five siblings. There is no when-not guidance and no named alternative, leaving the agent to infer the routing decision.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds the analysis scope (accessibility, token, specificity, typography, motion, copy, generic-default, proof checks), which is useful context, but says nothing about output format, severity levels, or whether any fix suggestions are returned.

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 sentence with the verb and resource front-loaded and the check categories packed efficiently. Nothing is wasted and nothing is repeated from the title.

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?

There is no output schema, so the description carries the burden of describing what comes back; it names the problem categories but never says whether the result is a report, a list of findings, a pass/fail, or how 'file_name' shapes that report. For a no-output-schema validation tool this leaves a real gap.

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% with only two simple parameters, so the schema already documents both 'code_snippet' and 'file_name'. The description adds no format, language-detection, or size-limit guidance beyond what the schema states.

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 ('Check') plus the resource (TSX, JSX, HTML or CSS snippet) and enumerates the exact problem classes it looks for. This is clearly distinguishable from the sibling tools, which are all design-system lookups (list_components, get_design_tokens, etc.) rather than validators.

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 implies you call it when you have a composition snippet to inspect, but there is no explicit when-to-use, no prerequisites, and no routing away from siblings. An agent must infer the trigger condition from the purpose statement alone.

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