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

Even though the readOnlyHint annotation already signals safety, the description goes well beyond it by disclosing exact resolution behavior: same-name resolution by context path scope, error behavior when not found, the meaning of each detail projection, and the static-source-facts caveat. It also precisely describes the ambiguous-match response shape with { ambiguous, matches, instruction } and instructs the agent to follow the instruction rather than pick arbitrarily.

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 dense but every sentence adds distinct value: purpose, read-only guarantee, context semantics, return behavior, detail options, static facts caveat, ambiguity protocol, and usage alternative. It is front-loaded with the core lookup purpose and then layers essential behavioral details without redundancy.

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 there is no output schema, the description thoroughly explains return values, error cases, ambiguity handling, and parameter behaviors. It covers all necessary contingencies for correct invocation and interpretation, including how to disambiguate by rationale.when and when to ask the user. The description is complete for a tool of this 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 description coverage is 0%, so the description carries the full burden, and it succeeds. It explains that 'name' can be either a name or id, that 'context' is used for path-scoped resolution of same-name components, and it defines each enum value of 'detail' with concrete projections. This adds substantial meaning beyond the bare schema types and enum list.

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 looks up a component by name or id, with an explicit read-only guarantee. It differentiates itself from the sibling get_design_context by noting that the sibling provides the list of all components. The verb 'look up' plus the resource 'component' makes 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 gives explicit when-to-use guidance: use this tool when you need implementation details for a known component to reuse rather than recreate it. It also names the alternative get_design_context for listing all components, preventing misuse. The ambiguity-resolution instructions further guide the agent on what to do when lookup returns multiple matches.

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?

Despite having readOnlyHint, description adds behavior details: read-only nature, output structure (JSON with conflict count, actionable count, list with fields), and parameter defaults. No contradiction.

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 compact and well-organized: action, behavior, output, parameters, and usage guidance all covered in 3 sentences without redundancy or unnecessary detail.

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?

Comprehensive for a tool with 2 optional params and no output schema: explains purpose, output shape, parameter semantics, and alternatives. No missing critical information.

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 only provides type/status as strings without descriptions. Description fully explains allowed values ('all'|'token'|'component', 'all'|'pending'|'resolved') and defaults (all), compensating for schema gaps.

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 the tool returns conflicts between design sources, with a specific verb and resource. Differentiates from siblings by explicitly directing resolved-value lookups to get_token/get_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?

Explicitly states when to use (audit disagreements between sources) and when not to (for resolved values, use other tools). Provides context with example (Figma vs codebase).

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?

Annotation readOnlyHint is reinforced and expanded with 'no side effects' and details about error behavior for unknown categories, adding value beyond annotations. No contradiction.

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 dense and structured, front-loading purpose with subsequent sentences adding detail. Slightly verbose but each clause carries useful info.

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, it describes the default summary output and category-specific detail, including error handling for unknown categories, making it complete for the agent to assess its 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 0%, so description fully compensates by explaining category values ('all', 'tokens', 'components', 'conflicts') and tokenCategory list, plus behavior for valid and invalid inputs.

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 gets the resolved design system context, distinguishes it from lookups by name with 'For lookups by name, use get_token or get_component instead.'

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 this as the first call to understand what exists, and names alternatives for specific lookups, providing clear context for when to use versus not.

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

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

Annotations already declare readOnlyHint=true, and the description repeats that fact. It adds useful behavioral context beyond the annotation: returns a JSON list with category/pattern/confidence, errors if no rules have been generated, and supports filtering by category.

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 dense but front-loaded, with every sentence adding value: purpose, safety, return shape, filter usage, and alternative tools. No wasted words or repetition of schema-only 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 tool is simple (one optional parameter, no output schema), and the description covers the return format, error case, filter values, and usage context. It is fully adequate for correct tool invocation.

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 fully compensates by enumerating exact accepted values: spacing, colors, typography, borderRadius, naming, components. It also explains that omitting the parameter returns all rules.

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: "Get the design rules inferred from your codebase patterns." It clearly differentiates from siblings by naming get_token and get_conflicts as alternatives for other intents.

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 when to use the tool ("understand implicit conventions") and provides exclusions: "For explicit design token values, use get_token. For source conflicts, use get_conflicts." Also explains category filtering and omission behavior.

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?

Although annotations already declare readOnlyHint=true, the description adds meaningful behavioral detail: 'Read-only, no side effects,' explains the return value, and discloses the error condition when the token is not found. It also explains alias normalization for categories, which goes beyond the annotation.

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 three well-structured sentences, with the primary action and read-only guarantee front-loaded, followed by return/error behavior, then category semantics and sibling-tool guidance. Each sentence earns its place, though the category-alias list makes it slightly denser than strictly necessary.

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 two-parameter look-up tool, the description is complete: it covers input semantics, return behavior, error outcome, category normalization, and alternative tool usage. No output schema is present, but the description explicitly lists what the return contains and the error case, so the agent can predict behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero description coverage, so the description carries the full burden of explaining parameters. It explains that 'name' is the token name to search for and 'category' narrows the search, listing all valid categories and alias normalization behavior. This adds substantial meaning beyond the raw 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's purpose: 'Look up a specific design token by name' and specifies the exact resource (design tokens), the return value, and the error behavior. It is distinguished from sibling tools like get_design_context by explicitly targeting single-token lookup vs broad overview.

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 when-to-use guidance: 'Use this when you know the token name.' It also provides an explicit alternative for a different use case: 'For a broad overview of all tokens, use get_design_context with category 'tokens' instead.' This is model guidance for tool selection.

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

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

The description states 'Read-only, no side effects,' which aligns with and expands on the readOnlyHint annotation. It additionally discloses return structure, filtering behavior, and the fact that hardcoded values are only detected for certain categories. This provides rich behavioral context beyond the annotation.

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 efficiently structured: it defines the topic, states safety, summarizes output, explains the parameter, and gives usage guidance. No sentence is wasted; it remains readable while packing substantial 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?

Even without an output schema, the description thoroughly details the return JSON structure (count, suggestion-coverage stats, list with file:line:column, literal, utility, smart-match suggestion). It covers the parameter, use cases, and alternatives, making the tool fully understandable for an agent.

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 fully compensates by explaining that the `category` parameter filters results and lists allowed values ('all' | 'colors' | 'spacing'), also noting why these categories matter. This adds essential meaning not present in 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 the tool's function: getting hardcoded token values (literals in source code instead of design tokens). It distinguishes itself from siblings by explicitly referencing get_design_context and get_token as alternatives for available tokens, and by describing its specific output related to violations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: 'Call this BEFORE generating UI with literal values — prefer the suggested token over a hardcoded literal.' It also names alternative tools for token lookup, giving clear when-to-use vs. when-not-to-use direction.

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