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

No annotations are provided, so the description carries full burden for behavioral disclosure. While it mentions the output characteristics ('shorter, more focused testing instructions'), it doesn't address important behavioral aspects like whether this is a read-only operation (implied but not stated), whether it requires authentication, potential rate limits, error conditions, or what happens if the component doesn't exist. For a tool with no annotation coverage, this is insufficient.

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 perfectly concise - two clear sentences that each earn their place. The first sentence states the core purpose, the second adds valuable context about the output format. No wasted words, front-loaded with the essential 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 the tool's relative simplicity (2 required parameters, no output schema, no annotations), the description is minimally adequate. It explains what the tool returns but doesn't address the broader context of when to use it among many siblings or important behavioral considerations. For a read operation in a crowded namespace, more guidance would be helpful, but the basics are 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 both parameters are well-documented in the schema itself. The description doesn't add any parameter-specific information beyond what's in the schema - it doesn't explain what 'condensed' means in relation to the platform/component parameters or provide examples of component names beyond the schema's example. With complete schema coverage, the 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 clearly states the tool's purpose: 'Get condensed acceptance criteria for a component' with the specific verb 'Get' and resource 'acceptance criteria', and adds useful context about the output being 'shorter, more focused testing instructions'. However, it doesn't explicitly differentiate this tool from its many siblings (like get_component_gherkin or search_*_criteria), which would be needed for a perfect score.

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. With 10 sibling tools including get_component_gherkin, search_native_criteria, and search_web_criteria, the agent has no indication of when this condensed format is preferred over other formats or search methods. The description only states what the tool does, not when to choose it.

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 mentions what content is included (code examples, WCAG mappings, technical guidance), which adds some behavioral context beyond the basic 'get' operation. However, it lacks details on permissions, rate limits, error handling, or response format, which are important for a tool with no output 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 front-loaded with the core purpose in the first sentence, followed by a concise list of included content types. Both sentences earn their place by adding value without redundancy, making 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?

Given no annotations and no output schema, the description provides basic purpose and content types but lacks completeness for a tool with two required parameters and multiple siblings. It doesn't clarify differences from similar tools (e.g., get_component_native_notes) or detail output structure, leaving gaps in contextual understanding.

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 both parameters clearly documented in the schema (platform with enum values, component with examples). The description doesn't add any parameter-specific information beyond what the schema provides, such as explaining how component names are formatted or platform implications. Baseline 3 is appropriate since the schema does the heavy lifting.

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 ('Get') and resource ('developer implementation notes for a component'), specifying what the tool does. It distinguishes from siblings by focusing on developer notes rather than other component data types like condensed views or Gherkin specifications, though it doesn't explicitly name alternatives.

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 by mentioning 'developer implementation notes' and listing content types (code examples, WCAG mappings, technical guidance), suggesting it's for technical/development purposes. However, it doesn't explicitly state when to use this tool versus sibling tools like get_component_native_notes or get_web_component, nor does it provide exclusions or prerequisites.

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 states the tool retrieves criteria but doesn't describe output format, pagination, error handling, or rate limits. It mentions the criteria are 'detailed' and for 'testing accessibility,' adding some context, but lacks critical behavioral traits like whether it returns structured data, requires authentication, or has side effects.

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, efficient sentence that front-loads the core purpose ('Get Gherkin-style acceptance criteria for a component') and adds clarifying details without waste. Every word earns its place, making it highly concise and well-structured for quick understanding.

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 moderate complexity (2 required parameters, no output schema, no annotations), the description is minimally adequate. It explains what the tool does but lacks details on output format, error cases, or integration with sibling tools. Without annotations or output schema, more behavioral context would improve completeness, but it meets the baseline for a read 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%, with clear descriptions for both parameters (platform and component). The description adds no additional parameter semantics beyond what the schema provides, such as examples for component beyond 'button' or 'checkbox,' or clarifications on platform implications. Baseline 3 is appropriate since the schema adequately documents 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 clearly states the tool's purpose: 'Get Gherkin-style acceptance criteria for a component' with the specific format 'Given/When/Then scenarios for testing accessibility.' It distinguishes from siblings by focusing on Gherkin-style criteria rather than condensed notes, developer notes, or component listings. However, it doesn't explicitly contrast with search_criteria tools, keeping it from a perfect 5.

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 get_component_condensed, get_component_developer_notes, search_native_criteria, or search_web_criteria. It mentions the criteria are 'for testing accessibility,' which hints at context, but offers no explicit when/when-not rules or prerequisites for selection 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 are provided, so the description carries the full burden of behavioral disclosure. It mentions retrieving notes but doesn't cover aspects like whether this is a read-only operation, potential rate limits, authentication needs, error handling, or what the return format looks like. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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, efficient sentence that front-loads the core purpose without unnecessary words. Every part earns its place by specifying what is retrieved and the scope, making it easy to parse quickly.

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 moderate complexity (2 required parameters, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose but lacks details on usage context, behavioral traits, and output, which are needed for a complete understanding. Without annotations or output schema, more elaboration would be beneficial.

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 description coverage is 100%, with clear descriptions for both parameters ('platform' and 'component'), including an enum for 'platform'. The description adds minimal value beyond the schema by specifying 'iOS or Android' and 'developer notes', but doesn't provide additional syntax, format details, or examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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 with a specific verb ('Get') and resource ('platform-specific developer notes for native components'), and specifies the scope ('iOS or Android implementation details'). However, it doesn't explicitly differentiate from sibling tools like 'get_component_developer_notes' or 'get_native_component', which appear 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 provides no guidance on when to use this tool versus alternatives. With multiple sibling tools involving components and notes (e.g., 'get_component_developer_notes', 'get_native_component'), there's no indication of context, prerequisites, or exclusions to help an agent choose appropriately.

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 describes the return content (iOS/Android details, properties, code examples) and implies a read-only operation, but does not cover aspects like error handling, rate limits, authentication needs, or data freshness. It adds some value by specifying the scope of returned data, but misses key behavioral traits for a tool with no annotation coverage.

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 purpose and efficiently lists return details without unnecessary words. Every part earns its place by clarifying the tool's function and output, making it highly concise and easy to parse.

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 annotations, no output schema, and 2 parameters with full schema coverage, the description is adequate but incomplete. It covers the purpose and return scope, but lacks details on error cases, response format, or usage prerequisites. For a tool with no structured behavioral data, it should provide more context to be fully helpful.

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 fully documents both parameters ('component' and 'include_code_examples'). The description does not add any meaning beyond what the schema provides, such as explaining parameter interactions or providing examples not in the schema. Baseline 3 is appropriate when the schema does all the work.

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 specific action ('Get detailed accessibility criteria') and target resource ('for a specific native component'), distinguishing it from siblings like 'get_component_condensed' or 'get_web_component' by specifying native components and detailed criteria. It explicitly mentions the return content (iOS/Android details, properties, code examples), making the purpose unambiguous and distinct.

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 native components (vs. web components) and detailed criteria (vs. condensed versions), but does not explicitly state when to use this tool over alternatives like 'get_component_condensed' or 'search_native_criteria'. It provides some context through the return details, but lacks clear exclusions or named alternatives, leaving room for interpretation.

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 mentions the return content but does not specify whether this is a read-only operation, if it requires authentication, rate limits, error handling, or pagination. For a tool with zero annotation coverage, this leaves significant behavioral gaps.

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, efficient sentence that front-loads the core purpose and lists return details without redundancy. Every word adds value, and there is no wasted text, making it highly concise 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?

Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is minimally adequate. It covers the purpose and return types but lacks behavioral context and usage guidelines. Without an output schema, it should ideally detail return structure, but the mention of specific return content partially compensates.

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 both parameters fully. The description adds no additional meaning beyond what the schema provides (e.g., it doesn't explain component naming conventions or code example formats). Baseline 3 is appropriate as the schema handles parameter documentation.

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 specific action ('Get detailed accessibility criteria') and resource ('for a specific web component'), distinguishing it from siblings like 'list_web_components' (which lists components) and 'search_web_criteria' (which searches criteria). It explicitly mentions the return content (acceptance criteria, WCAG mappings, etc.), making the purpose unambiguous and distinct.

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 'get_component_condensed' or 'search_web_criteria'. It lacks context about prerequisites (e.g., needing a component name from a list) or exclusions (e.g., not for native components), leaving the agent to infer usage from tool names 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 full burden of behavioral disclosure. It states the tool lists formats but doesn't cover critical aspects like whether it's a read-only operation, potential side effects, error handling, rate limits, or authentication needs. For a tool with no annotation coverage, this lack of behavioral context is a significant gap, though it doesn't contradict any annotations.

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, efficient sentence that front-loads the core purpose ('List all available content formats for a specific component') and includes helpful examples ('e.g., gherkin, condensed, developer notes'). There is no wasted text, and every word contributes to clarifying the tool's function, making it appropriately concise 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?

Given the tool's low complexity (2 required parameters, no output schema, no nested objects) and high schema coverage, the description is minimally adequate. It explains what the tool does but lacks details on behavioral traits, usage guidelines, and output format, which are important for a tool with no annotations. This results in a basic but incomplete understanding, suitable for a score of 3.

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 description coverage is 100%, with both parameters (platform and component) well-documented in the input schema. The description adds no additional parameter semantics beyond implying the component name examples (e.g., 'button', 'checkbox') align with the schema. This meets the baseline score of 3, as the schema adequately handles parameter documentation without needing extra details from the description.

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: 'List all available content formats for a specific component' with examples like 'gherkin, condensed, developer notes'. This specifies the verb ('List'), resource ('content formats'), and scope ('for a specific component'), making it easy to understand what the tool does. However, it doesn't explicitly distinguish it from sibling tools like get_component_condensed or get_component_gherkin, which might retrieve specific formats rather than list them all.

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 doesn't mention sibling tools such as get_component_condensed or list_web_components, nor does it specify prerequisites, exclusions, or contextual cues for selection. This leaves the agent without explicit usage instructions, relying solely on inference from the tool name and 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions listing components and optional filtering, but does not cover critical aspects such as pagination behavior, rate limits, authentication needs, or what the output format looks like (e.g., list structure, fields included). This is a significant gap for a tool with no annotation coverage.

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 core purpose and efficiently includes the optional filtering detail in a single, clear sentence. There is no wasted text, making it appropriately sized and easy to parse.

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 low complexity (1 optional parameter, no output schema, no annotations), the description is somewhat complete but lacks depth. It covers the basic purpose and parameter use, but without annotations or output schema, it should ideally include more behavioral context (e.g., response format, limitations) to fully guide the agent, resulting in an adequate but not thorough description.

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 adds minimal value beyond the input schema, which has 100% coverage for the single parameter 'category'. It mentions 'Optionally filter by category', aligning with the schema's description, but does not provide additional semantics like example categories beyond 'controls' or 'components' or explain how filtering works. With high schema coverage, the 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 clearly states the verb ('List') and resource ('native (iOS/Android) accessibility components from MagentaA11y'), making the purpose specific. It also distinguishes from siblings like 'list_web_components' by specifying 'native' components and from 'get_native_component' by indicating a list operation rather than retrieving a single 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 description provides clear context for usage by mentioning optional filtering by category, which helps guide when to use this tool. However, it does not explicitly state when not to use it or name alternatives (e.g., 'search_native_criteria' for more complex queries), leaving room for improvement in sibling differentiation.

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 behavioral disclosure. It describes a read operation ('List') but lacks details on permissions, rate limits, pagination, or response format. This leaves significant gaps in understanding how the tool behaves beyond basic functionality.

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, efficient sentence that front-loads the core action ('List all available web accessibility components') and includes optional filtering details without unnecessary elaboration. Every part of the sentence serves a clear purpose, making it highly concise 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?

Given the lack of annotations and output schema, the description is incomplete for a tool that likely returns a list of components. It does not explain the return format, such as whether it includes IDs, names, or other metadata, nor does it address potential limitations or error handling, leaving key contextual gaps.

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% description coverage, clearly documenting the optional 'category' parameter. The description adds minimal value by mentioning filtering examples ('e.g., controls, forms, components'), which slightly enhances understanding but does not go beyond what the schema provides, aligning with the baseline 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 clearly states the verb ('List') and resource ('all available web accessibility components from MagentaA11y'), making the purpose specific and understandable. However, it does not explicitly differentiate this tool from its siblings like 'list_native_components' or 'get_web_component', which limits the score to 4 instead of 5.

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, such as 'list_native_components' for native components or 'get_web_component' for detailed information on a specific component. It mentions optional filtering but does not specify scenarios or exclusions, resulting in minimal usage 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the search functionality and platforms, it lacks details about permissions, rate limits, pagination, error handling, or what the results look like (especially since there's no output schema). This leaves significant gaps for a search 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?

The description is two concise sentences with zero waste: the first states the action and mechanism, and the second specifies the context and differentiation. Every word earns its place, and it is front-loaded with the core 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?

Given the complexity of a search tool with no annotations and no output schema, the description is incomplete. It lacks information about result format, error conditions, or behavioral traits like rate limits. While it covers purpose and context well, it does not provide enough operational guidance for an AI agent to use it effectively without trial and error.

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 description coverage is 100%, so the schema already fully documents both parameters (query and max_results). The description adds no additional parameter semantics beyond what's in the schema, such as examples of effective queries or constraints on max_results. Baseline 3 is appropriate when schema does the heavy lifting.

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 ('Search') and resource ('native accessibility criteria'), specifies the search mechanism ('using keywords'), and distinguishes it from sibling tools by focusing on platform-specific iOS/Android details rather than web components or other formats mentioned in sibling names like 'search_web_criteria'.

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 for when to use this tool ('Find platform-specific implementation details for iOS (VoiceOver) and Android (TalkBack)'), which implicitly differentiates it from web-focused alternatives. However, it does not explicitly state when NOT to use it or name specific alternative tools like 'search_web_criteria'.

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 mentions searching but doesn't disclose behavioral traits like whether this is a read-only operation, how results are ranked/limited, error conditions, or performance characteristics. The description is functional but lacks transparency about how the tool behaves beyond the basic 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 extremely concise (two sentences) and front-loaded with the core purpose. Every sentence earns its place: the first states the action and scope, the second provides concrete examples. There's zero wasted text or 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 the tool's moderate complexity (search operation with 2 parameters), 100% schema coverage, but no annotations or output schema, the description is minimally complete. It covers what the tool does and provides examples, but lacks details about return format, error handling, or behavioral constraints that would be helpful 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?

Schema description coverage is 100%, so the schema already documents both parameters (query and max_results) thoroughly. The description adds no additional parameter semantics beyond what's in the schema, maintaining the baseline score of 3 for adequate but not enhanced parameter explanation.

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: 'Search web accessibility criteria using keywords' with specific examples of what can be searched (WCAG guidelines, implementation patterns, accessibility requirements). It distinguishes from sibling tools by focusing on 'web' accessibility criteria rather than native components, though it doesn't explicitly contrast with 'search_native_criteria'.

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 through the examples ('WCAG guidelines, implementation patterns, or specific accessibility requirements'), suggesting this tool is for finding accessibility standards. However, it doesn't provide explicit guidance on when to use this versus the sibling 'search_native_criteria' tool or other search/list tools, nor does it mention prerequisites or exclusions.

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