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. It only states the action ('analyze') without detailing what the tool does operationally: whether it fetches data, computes metrics, generates reports, or requires specific permissions. There's no mention of output format, error handling, rate limits, or authentication needs, leaving critical behavioral traits unspecified.

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 with no wasted words. It is front-loaded and efficiently states the core function. However, this brevity comes at the cost of completeness, as it lacks necessary details for effective tool use.

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 (7 parameters, no schema descriptions, no annotations) and the presence of an output schema, the description is insufficient. While the output schema may cover return values, the description fails to provide context on tool behavior, parameter meanings, or usage scenarios. For a tool with multiple parameters and no annotation support, this minimal description leaves significant gaps in 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 0%, meaning none of the 7 parameters have descriptions in the schema. The tool description adds no information about parameters, failing to compensate for the lack of schema documentation. Parameters like 'region_name', 'period', and authentication fields ('profile_name', 'role_arn', etc.) are entirely unexplained, leaving their purposes and usage ambiguous.

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 'Analyze API Gateway performance metrics' restates the tool name with minimal elaboration. It specifies the resource (API Gateway) and general action (analyze performance metrics) but lacks specificity about what analysis entails or what metrics are examined. Compared to siblings like 'analyze_cloudfront_cache_hit_ratio' or 'analyze_dynamodb_throttling', it doesn't clearly differentiate its scope beyond the resource type.

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 prerequisites, appropriate contexts, or exclusions. Given the sibling tools include various analysis functions (e.g., cost analysis, performance insights), there's no indication of when API Gateway performance analysis is preferred over other tools or what problem it addresses specifically.

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 'analyze,' implying a read-only operation, but doesn't clarify if it requires authentication (e.g., via AWS credentials), involves data retrieval from CloudFront metrics, or has any side effects like rate limits. The description lacks essential behavioral context for a tool with 7 parameters related to AWS access.

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 with no wasted words. It's front-loaded and appropriately sized for conveying the basic purpose, though this conciseness comes at the cost of detail in other dimensions.

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 (7 parameters, no annotations, but with an output schema), the description is incomplete. It doesn't address parameter meanings, authentication needs, or behavioral traits. While the output schema may cover return values, the description lacks context for proper tool invocation, especially for an AWS analysis tool with multiple credential options.

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 mentions 'CloudFront cache hit ratios' but doesn't explain any of the 7 parameters (e.g., 'region_name', 'period', 'profile_name'). With 0% schema description coverage, the schema only provides titles and types without meaning. The description fails to compensate, leaving parameters like 'role_arn' and 'access_key' undocumented in terms of their purpose or usage.

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 'Analyze CloudFront cache hit ratios' clearly states the verb ('analyze') and resource ('CloudFront cache hit ratios'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'analyze_api_gateway_performance' or 'analyze_data_transfer_costs' beyond specifying the CloudFront service, leaving the scope somewhat vague compared to more specific 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 provides no guidance on when to use this tool versus alternatives. With many sibling tools focused on analysis (e.g., 'analyze_api_gateway_performance'), there's no indication of context, prerequisites, or exclusions, leaving the agent to infer usage based solely on the tool name.

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 'using AWS Cost Explorer,' implying it might query AWS services, but doesn't specify authentication requirements, rate limits, data freshness, or output format. For a tool with 6 parameters and no annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence with zero waste: 'Analyze data transfer costs using AWS Cost Explorer.' It's appropriately sized and front-loaded, clearly stating the core function without unnecessary 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?

Given the tool's complexity (6 parameters, no annotations) and the presence of an output schema, the description is minimally adequate. The output schema likely handles return values, reducing the burden on the description. However, with no parameter semantics and limited behavioral context, it's incomplete for effective use, though not entirely inadequate.

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%, meaning none of the 6 parameters are documented in the schema. The description doesn't add any parameter information—it doesn't explain what 'region_name,' 'profile_name,' or other fields mean or how they affect the analysis. This fails to compensate for the low schema coverage, leaving parameters largely unexplained.

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 the tool 'Analyze data transfer costs using AWS Cost Explorer,' which provides a clear verb ('analyze') and resource ('data transfer costs'). However, it doesn't differentiate from sibling tools like 'get_cost_by_region' or 'generate_cost_allocation_report,' which also involve cost analysis. The purpose is clear but lacks sibling distinction.

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

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

No guidance is provided on when to use this tool versus alternatives. With many sibling tools related to cost analysis (e.g., 'get_cost_by_region,' 'generate_cost_allocation_report'), the description fails to specify context, prerequisites, or exclusions. This leaves the agent without direction on 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool analyzes for throttling issues, implying a read-only diagnostic operation, but doesn't specify what the analysis entails (e.g., metrics examined, timeframes, output format), whether it requires specific AWS permissions, or if it has side effects like data collection. For a tool with 7 parameters and no annotations, 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: 'Analyze DynamoDB tables for throttling issues.' It's front-loaded with the core action and resource, with zero wasted words. This is appropriately concise for a tool name that already hints at the function, though the brevity contributes to gaps in other dimensions.

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 (7 parameters, no annotations, but an output schema exists), the description is incomplete. While the output schema may cover return values, the description lacks context on authentication needs (multiple credential parameters), analysis scope, or behavioral traits. For a diagnostic tool with many parameters, more guidance is needed to help an agent use it effectively.

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 7 parameters with 0% description coverage (only titles like 'Region Name', 'Period'), so the description must compensate. However, it adds no parameter information beyond what's implied by the tool's purpose (e.g., 'region_name' for AWS region, 'period' for analysis duration). It doesn't explain parameter interactions, defaults, or why multiple authentication options exist. With low schema coverage, the description fails to provide adequate semantic context.

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 'Analyze DynamoDB tables for throttling issues' clearly states the verb ('analyze'), resource ('DynamoDB tables'), and purpose ('for throttling issues'), which is adequate. However, it doesn't distinguish this tool from its many siblings (e.g., 'find_overutilized_dynamodb_tables', 'find_underutilized_dynamodb_tables', 'find_unused_dynamodb_tables'), which all involve analyzing DynamoDB tables for different issues. The purpose is clear but lacks sibling differentiation.

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 prerequisites (e.g., AWS credentials, permissions), specific scenarios for throttling analysis, or how it differs from other DynamoDB-related tools in the sibling list. Without such context, an agent must infer usage from the name alone, which is insufficient.

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. The description only states the purpose without any behavioral traits: it doesn't specify if this is a read-only operation, what data sources it uses (e.g., CloudWatch logs), potential side effects, authentication requirements, rate limits, or output format. For a tool with 7 parameters related to AWS access, this lack of transparency is a significant 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, efficient sentence with zero waste. It's appropriately sized for a simple purpose statement and front-loaded with the core action ('Analyze Lambda functions for cold start issues'). There's no unnecessary elaboration 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 complexity (7 parameters, AWS-related tool) and the presence of an output schema (which might help with return values), the description is incomplete. It lacks essential context: no behavioral details (critical with no annotations), no parameter explanations (with 0% schema coverage), and no usage guidelines. While the output schema might cover return values, the description fails to provide enough information for effective tool selection and invocation in a multi-tool environment.

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%, meaning none of the 7 parameters have descriptions in the schema. The description adds no information about any parameters—it doesn't mention region, period, or authentication details. With 0% coverage and no compensation in the description, the parameters remain undocumented, making it difficult for an agent to understand their purpose or usage.

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 the tool's purpose as analyzing Lambda functions for cold start issues, which is clear but vague. It specifies the resource (Lambda functions) and the type of analysis (cold start issues), but lacks specificity about what 'analyze' entails (e.g., identifying, measuring, or reporting). It distinguishes from siblings by focusing on Lambda cold starts, but doesn't clarify how it differs from similar tools like 'analyze_lambda_performance' (not in the list) or 'find_underutilized_lambda_functions' (which might overlap).

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 prerequisites (e.g., AWS credentials setup), context (e.g., performance troubleshooting), or exclusions (e.g., not for cost analysis). Given the sibling tools include various analysis and optimization tools, there's no indication of when this specific cold start analysis is preferred over others like 'get_cost_optimization_lambda' or general performance tools.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action ('analyze') without detailing what the analysis entails (e.g., read-only vs. destructive, authentication requirements, rate limits, or output format). For a tool with 7 parameters and no annotation coverage, this is a significant gap in transparency about how the tool behaves.

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 with no wasted words. It is appropriately sized for a basic statement of purpose, though it lacks depth. The structure is straightforward, but the brevity contributes to under-specification rather than optimal clarity.

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 (7 parameters, no annotations, but an output schema exists), the description is incomplete. It doesn't explain what the analysis outputs, how parameters interact, or behavioral traits. While the output schema may cover return values, the description fails to provide necessary context for selecting and invoking the tool effectively, especially compared to detailed sibling tools.

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%, meaning none of the 7 parameters have descriptions in the schema. The tool description does not mention any parameters, failing to compensate for this gap. Parameters like 'region_name', 'period', and authentication fields ('profile_name', 'role_arn', etc.) are left unexplained, leaving the agent to guess their purposes and usage.

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 the tool analyzes RDS Performance Insights data, which provides a clear verb ('analyze') and resource ('RDS Performance Insights data'). However, it lacks specificity about what kind of analysis it performs (e.g., identifying bottlenecks, generating reports, or providing metrics) and doesn't distinguish it from sibling tools that also analyze AWS resources. The purpose is understandable but vague.

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 many sibling tools focused on AWS analysis (e.g., 'analyze_dynamodb_throttling', 'find_overutilized_rds_instances'), there's no indication of whether this tool is for performance monitoring, cost optimization, or troubleshooting. No prerequisites, exclusions, or comparative context are mentioned.

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 performs analysis, implying a read-only operation, but doesn't specify if it requires specific permissions, how it handles authentication, what the output format is, or any rate limits. The description is too brief to provide meaningful behavioral context 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 a single, concise sentence that directly states the tool's function without unnecessary words. It is front-loaded and efficient, though it could benefit from more detail to improve clarity and completeness.

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 complexity (6 parameters, no schema descriptions, no annotations) and the presence of an output schema, the description is incomplete. It doesn't explain the analysis scope, output format, or parameter usage, leaving significant gaps. While the output schema may cover return values, the description fails to provide enough context for effective tool selection and 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 description coverage is 0%, so the schema provides no parameter details. The description adds no information about the six parameters (e.g., region_name, profile_name, role_arn, access_key, secret_access_key, session_token), their purposes, or how they affect the analysis. This leaves parameters undocumented and unclear to the agent.

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 the tool's purpose as analyzing Reserved Instance utilization and coverage, which is clear but vague. It specifies the resource (Reserved Instances) but lacks details on what analysis entails or what specific metrics are examined. It distinguishes from siblings by focusing on Reserved Instances, but doesn't explain how it differs from similar tools like 'get_reserved_instance_recommendations'.

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 prerequisites, such as needing AWS credentials, or compare it to sibling tools like 'get_reserved_instance_recommendations' for decision-making. Without this context, the agent must infer usage from the tool name 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. The description only states what the tool does at a high level without revealing any behavioral traits such as whether it's read-only or destructive, what permissions or authentication are needed (though parameters hint at AWS auth), rate limits, or what the analysis output entails. For a tool with 7 parameters and no annotations, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence that states the core purpose without unnecessary words. It is appropriately sized and front-loaded, making it easy to parse quickly. Every word earns its place, though it could benefit from more detail given the tool's complexity.

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 complexity (7 parameters, no annotations, schema coverage 0%), the description is incomplete. While an output schema exists (which might explain return values), the description lacks essential context such as behavioral traits, parameter meanings, and differentiation from siblings. For a tool with significant input complexity and no annotation support, the description does not provide enough information for effective 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 description coverage is 0%, meaning none of the 7 parameters have descriptions in the schema. The tool description does not mention any parameters or provide context about what they mean, such as explaining 'required_tags' or the AWS authentication parameters. With low schema coverage and no parameter information in the description, it fails to compensate, leaving parameters largely undocumented.

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 the tool's purpose as analyzing tag compliance across AWS resources, which is clear but vague. It specifies the action (analyze) and resource scope (AWS resources) but doesn't distinguish it from sibling tools like 'find_untagged_resources' or explain what 'compliance' entails. The purpose is understandable but lacks specificity about what the analysis produces or how it differs from similar 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 provides no guidance on when to use this tool versus alternatives. With sibling tools like 'find_untagged_resources' that seem related, there's no indication of how this tool differs or when it should be preferred. The description doesn't mention prerequisites, context, or exclusions, leaving the agent with no usage direction.

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. It discloses the tool's purpose and return type (dictionary with ASGs using old AMIs), but lacks details on behavioral traits such as required AWS permissions, potential rate limits, whether it performs read-only operations (implied by 'Find'), or error handling. The description does not 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 well-structured and front-loaded with the core purpose, followed by organized sections for arguments and returns. Each sentence earns its place by clarifying parameters and output without redundancy, making it efficient 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 complexity (8 parameters, no annotations, but with an output schema indicated), the description is largely complete. It explains the tool's purpose, parameters, and return type. However, it could improve by addressing behavioral aspects like permissions or limitations, though the output schema may cover return values. It's adequate but has minor gaps in behavioral context.

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 must compensate fully. It provides detailed semantics for all 8 parameters, including their purposes (e.g., 'region_name: AWS region name', 'period: Minimum age in days for AMI to be considered old'), defaults, and optional status. This adds significant value beyond the bare 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 specific action ('Find Auto Scaling Groups using AMIs older than the specified period'), identifies the target resource (Auto Scaling Groups with old AMIs), and distinguishes it from siblings like 'find_unused_amis' (which finds unused AMIs) or 'find_ec2_instances_with_old_generations' (which focuses on instance generations rather than AMI age in ASGs).

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 identifying outdated AMIs in ASGs based on age, but does not explicitly state when to use this tool versus alternatives (e.g., 'find_ec2_instances_with_old_generations' for instance types, or 'find_unused_amis' for unused AMIs). It provides context (AWS region, AMI age threshold) but lacks explicit guidance on 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 full burden for behavioral disclosure. It states what the tool does but provides no information about permissions required, rate limits, whether this is a read-only operation, what format the results will be in, or any error conditions. For a tool with 6 authentication parameters, this is a significant 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, efficient sentence that gets straight to the point with zero wasted words. It's appropriately sized for what it does convey, though it's under-specified rather than concise.

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 has 6 parameters (all authentication-related with 0% schema coverage), no annotations, and sibling tools that suggest this is part of a cost/optimization analysis system, the description is severely incomplete. While an output schema exists, the description doesn't help the agent understand what 'old types' means, what authentication approach to use, or how this fits into broader optimization workflows.

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%, meaning none of the 6 parameters have descriptions in the schema. The tool description provides absolutely no information about any parameters - not even mentioning that authentication parameters exist. This leaves the agent completely in the dark about what inputs are needed.

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 ('find') and resource ('EBS volumes using previous generation volume types'), making the purpose immediately understandable. It doesn't explicitly differentiate from sibling tools like 'find_unused_volumes' or 'find_unencrypted_ebs_volumes', but the specific focus on 'old types' provides reasonable implicit distinction.

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 prerequisites, timing considerations, or how it differs from other volume-related tools in the sibling list. The agent must infer usage from the name 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'Find' which implies a read-only operation, but doesn't specify authentication requirements, rate limits, what constitutes 'old generations', whether it scans all instances or filtered ones, or the output format. This leaves significant gaps for a tool with 6 parameters.

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 directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded with the core functionality.

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 tool with 6 parameters, no annotations, and 0% schema description coverage, the description is insufficient. While an output schema exists (which helps), the description doesn't explain what 'old generations' means, how instances are identified, or provide any context about authentication/authorization despite having multiple credential parameters.

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 provides no information about any of the 6 parameters. With 0% schema description coverage and no parameter details in the description, the agent has no semantic understanding of what region_name, profile_name, role_arn, access_key, secret_access_key, or session_token mean in this context.

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 'Find' and the resource 'EC2 instances using previous generation instance types', making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'find_overutilized_ec2_instances' or 'find_underutilized_ec2_instances', which target different optimization dimensions.

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

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

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, timing considerations, or how it relates to sibling tools focused on EC2 optimization (e.g., cost, performance, or security tools).

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

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

With no annotations provided, the description carries full burden but only states what the tool does, not how it behaves. It doesn't disclose whether this is a read-only operation, potential side effects, authentication requirements, rate limits, or output format, which are critical for a tool with 7 parameters.

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 any wasted words. It's appropriately sized for a straightforward tool name and gets straight to the point.

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 complexity (7 parameters, no annotations, 0% schema coverage) and the presence of an output schema, the description is insufficient. It explains what the tool does but lacks crucial context about parameters, behavioral traits, and usage scenarios, making it incomplete for effective agent 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 0%, and the description provides no information about any of the 7 parameters. It doesn't explain what 'age_days' means in context, how AWS credentials are used, or the purpose of region selection, failing to compensate for the schema's lack of descriptions.

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 ('Find') and resource ('old ECS task definitions not used by any service'), distinguishing it from siblings like 'find_outdated_ecs_platform_versions' or 'find_unused_ecs_clusters_and_services'. It precisely defines the scope as task definitions that are both old and unused.

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, prerequisites, or exclusions. It lacks context about typical use cases (e.g., cleanup, cost optimization) or how it relates to sibling tools, leaving the agent to infer usage.

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 validation across multiple services but doesn't describe what 'orphaned' means operationally (e.g., alarms that reference deleted resources), whether this is a read-only operation, what permissions are needed, or how results are returned. For a tool with 7 parameters and no 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 appropriately sized and front-loaded: the first sentence states the core purpose, and the second adds specific context about validation scope. Both sentences earn their place by providing essential information without 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 tool's complexity (7 parameters, no annotations, but with an output schema), the description is partially complete. It clearly defines the tool's purpose and scope but lacks details on parameters, behavioral traits, and usage guidelines. The presence of an output schema means return values are documented elsewhere, but the description should still address more of the operational context.

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 0%, meaning none of the 7 parameters have descriptions in the schema. The tool description provides no information about any parameters—it doesn't explain what 'region_name', 'max_results', or authentication parameters like 'profile_name' and 'role_arn' are for. With low schema coverage, the description fails to compensate, leaving parameters undocumented.

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: 'Find CloudWatch alarms not associated with any active AWS resources.' This is a specific verb ('find') + resource ('orphaned CloudWatch alarms') combination that distinguishes it from siblings like 'find_unused_cloudwatch_alarms' (which likely finds alarms that aren't triggering) and 'find_orphaned_cloudwatch_dashboards' (which focuses on dashboards rather than alarms).

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 listing the AWS services it validates against (EC2, RDS, ECS, etc.), suggesting it's for cross-service resource validation. However, it doesn't explicitly state when to use this tool versus alternatives like 'find_unused_cloudwatch_alarms' or other sibling 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.

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 what the tool does but doesn't describe how it works—e.g., whether it scans all dashboards, requires specific permissions, has rate limits, returns a list or report, or what 'orphaned' means in practice. For a tool with 7 parameters and no annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, clear sentence with zero waste. It's front-loaded with the core purpose and appropriately sized for the tool's apparent complexity. Every word contributes directly to understanding what the tool does.

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 complexity (7 parameters, no annotations, but has an output schema), the description is incomplete. It lacks behavioral details, parameter explanations, and usage context. While the output schema might cover return values, the description doesn't compensate for the gaps in understanding how to invoke the tool effectively or what to expect beyond the basic purpose.

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%, meaning none of the 7 parameters have descriptions in the schema. The tool description adds no parameter information beyond what the schema provides (only titles and types). It doesn't explain what 'region_name', 'period', or authentication parameters like 'profile_name' do in the context of finding orphaned dashboards, leaving parameters largely undocumented.

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: 'Find CloudWatch dashboards with widgets referencing deleted resources.' It specifies the verb ('Find'), resource ('CloudWatch dashboards'), and scope ('with widgets referencing deleted resources'), which is specific and actionable. However, it doesn't explicitly differentiate from sibling tools like 'find_unused_cloudwatch_alarms' or 'find_unused_cloudwatch_log_groups', though the focus on 'orphaned' dashboards is 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. It doesn't mention prerequisites, typical scenarios, or how it differs from other 'find' tools in the sibling list. Without any usage context, an agent must infer its application solely from the purpose statement.

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. It states the tool finds outdated services but doesn't disclose behavioral traits like whether it's read-only (implied by 'find'), requires AWS authentication (hinted by parameters but not explained), returns a list or report format, has rate limits, or handles pagination. For a tool with 6 authentication parameters, this is a significant 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, clear sentence with zero waste. It's front-loaded with the core purpose and appropriately sized for a simple find operation. Every word earns its place 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 the tool's moderate complexity (6 auth parameters, AWS context) and the presence of an output schema (which should cover return values), the description is minimally complete. It states what the tool does but lacks context on authentication, usage, and behavioral details. With no annotations and poor parameter coverage, it's adequate but has clear gaps for an AWS 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?

Schema description coverage is 0%, so the schema provides only titles and types. The description adds no parameter information—it doesn't explain what 'region_name', 'profile_name', or other AWS auth parameters mean, their defaults, or how they interact. With 6 undocumented parameters, the description fails to compensate for the schema's lack of descriptions.

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: 'Find ECS services not using the latest platform version.' It specifies the verb ('find'), resource ('ECS services'), and criteria ('not using the latest platform version'). However, it doesn't explicitly differentiate from sibling tools like 'find_outdated_eks_cluster_versions' or 'find_outdated_elasticache_engine_versions' beyond the resource type.

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 prerequisites, context (e.g., cost optimization, security compliance), or how it relates to sibling tools like 'find_old_ecs_task_definitions' or 'find_underutilized_ecs_services'. The agent must infer usage from the tool name 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't describe how it works: whether it's a read-only scan, requires specific AWS permissions, has rate limits, returns structured data, or handles errors. For a tool with 6 parameters and no annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, clear sentence with zero wasted words. It's appropriately sized for a simple tool purpose statement and front-loaded with the core functionality, making it highly efficient in structure.

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 complexity (6 parameters, no annotations, but with an output schema), the description is incomplete. It states the purpose but doesn't address parameter usage, behavioral expectations, or how results are returned. The output schema existence means return values are documented elsewhere, but the description should still cover operational context given the parameter-heavy nature.

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 mentions no parameters at all, while the input schema has 6 parameters with 0% description coverage. Parameters like 'region_name', 'profile_name', 'role_arn', and authentication keys are completely undocumented in the description, failing to add any semantic meaning beyond the bare 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 verb ('find') and resource ('EKS clusters not running the latest Kubernetes version'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'find_outdated_ecs_platform_versions' or 'find_outdated_rds_engine_versions' beyond the resource type, missing specific sibling distinction.

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, prerequisites, or context. It lacks any mention of when this tool is appropriate compared to other 'find_outdated_' tools or general AWS analysis tools in the sibling list, leaving usage entirely implicit.

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 what the tool does but doesn't describe how it works—e.g., whether it scans all clusters, requires specific permissions, has rate limits, returns structured data, or handles errors. This leaves significant gaps for an agent to understand operational 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 directly states the tool's purpose without unnecessary words. It's front-loaded and wastes no space, 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 complexity (6 parameters, no annotations, but has an output schema), the description is insufficient. It explains the goal but lacks details on inputs, behavior, and how results are structured, leaving the agent with too many unknowns despite the output schema potentially covering return values.

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 6 parameters with 0% description coverage, and the tool description adds no information about any parameters. It doesn't explain what 'region_name', 'profile_name', or authentication parameters do, nor their relationships, leaving all parameters undocumented and unclear in usage.

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 'find' and resource 'ElastiCache clusters not running the latest engine version', making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'find_outdated_ecs_platform_versions' or 'find_outdated_rds_engine_versions' beyond the resource type, missing specific comparison points.

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 other 'find_outdated_' tools or general analysis tools in the sibling list. It lacks context about prerequisites, timing, or specific scenarios where this tool is most appropriate.

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 full burden for behavioral disclosure. It states what the tool does but doesn't describe how it works: no information about authentication requirements (despite 6 auth-related parameters), rate limits, whether it's read-only or destructive, what the output contains, or how it determines 'deprecated/outdated' status. This leaves significant gaps for an agent to use it correctly.

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 states the core purpose without unnecessary words. It's appropriately sized for a tool with this level of complexity and gets straight to the point.

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?

While an output schema exists (which helps with return values), the description is incomplete for a tool with 6 undocumented authentication parameters and no behavioral context. For a tool that likely requires AWS authentication and makes API calls, the description should at minimum mention authentication requirements or refer to the parameters. The current description leaves too many open questions for proper 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 description coverage is 0%, meaning none of the 6 parameters have descriptions in the schema. The tool description provides zero information about any parameters, not even mentioning that authentication parameters exist. This leaves all parameters completely undocumented, which is inadequate given the parameter count and complexity.

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 ('find') and resource ('Lambda functions with deprecated or outdated runtimes'), making the purpose immediately understandable. It distinguishes from some siblings (e.g., 'find_underutilized_lambda_functions') by focusing on runtime versions rather than utilization, but doesn't explicitly contrast with all similar tools like 'analyze_lambda_cold_starts'.

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 prerequisites, timing considerations, or how it differs from other lambda-related tools in the sibling list. The agent must infer usage from the tool name 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 'finds' instances, implying a read-only operation, but doesn't clarify if it requires specific AWS permissions, whether it scans all instances or uses filters, what the output format is, or if there are rate limits. For a tool with 6 parameters and no 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, clear sentence with zero waste. It's appropriately sized and front-loaded, directly stating the tool's purpose without unnecessary elaboration. Every word earns its place, making it easy for an agent 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 complexity (6 parameters, no annotations, but with an output schema), the description is incomplete. It doesn't address authentication needs, regional scoping, or how the tool determines 'latest engine version'. While the output schema may cover return values, the description lacks context on operational behavior and parameter usage, making it insufficient for an agent to use the tool effectively without additional inference.

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 no meaning beyond the input schema. With 6 parameters (region_name, profile_name, role_arn, access_key, secret_access_key, session_token) and 0% schema description coverage, the schema only provides titles and types. The description doesn't explain what these parameters do, how they interact (e.g., authentication precedence), or why they're needed. This fails to compensate for the low schema coverage.

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: 'Find RDS instances not running the latest engine version.' It specifies the verb ('find'), resource ('RDS instances'), and criteria ('not running the latest engine version'). However, it doesn't explicitly differentiate from sibling tools like 'find_outdated_ecs_platform_versions' or 'find_outdated_elasticache_engine_versions' beyond the RDS focus, which is implied but not contrasted.

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 prerequisites (e.g., AWS credentials), context (e.g., cost optimization vs. security), or comparisons to sibling tools like 'analyze_rds_performance_insights' or 'find_underutilized_rds_instances'. The agent must infer usage from the tool name 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It states what the tool does but doesn't mention authentication requirements (despite 6 auth-related parameters), rate limits, pagination, output format, or whether it's a read-only operation. The description is minimal and lacks crucial operational context.

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 - a single sentence that directly states the tool's purpose. There's no wasted language or unnecessary elaboration. It's front-loaded with the core functionality.

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 (6 parameters, 0% schema coverage, no annotations) and the fact this is a security analysis tool, the description is inadequate. While an output schema exists, the description doesn't provide enough context about authentication, regional scoping, or operational behavior for the agent to use this tool effectively.

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%, meaning all 6 parameters are undocumented in the schema. The description provides no information about any parameters, not even mentioning that region selection or authentication is required. This leaves the agent with no guidance on how to properly configure the tool.

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 ('Find') and resource ('security groups'), with precise criteria ('overly permissive rules (0.0.0.0/0 or ::/0)'). It distinguishes from sibling tools like 'find_unused_security_groups' by focusing on permission analysis rather than usage patterns.

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

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

No guidance is provided on when to use this tool versus alternatives. While the purpose is clear, there's no mention of prerequisites, typical use cases, or how it relates to other security analysis tools in the 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 states the tool finds tables with high utilization but doesn't describe what 'high capacity utilization' means (e.g., read/write capacity units), how it's measured, whether it's a read-only operation, what permissions are required, or what the output looks like. This is inadequate for a tool with 7 parameters and 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, efficient sentence that gets straight to the point: 'Find DynamoDB tables with high capacity utilization (>80%).' It's appropriately sized for a simple tool purpose, with no wasted words or unnecessary elaboration.

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 complexity (7 parameters, 0% schema coverage, no annotations) and the presence of an output schema, the description is incomplete. It doesn't explain parameter usage, behavioral traits, or how it differs from siblings. While the output schema might cover return values, the description lacks essential context for proper tool invocation and selection.

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 0%, meaning none of the 7 parameters are documented in the schema. The description mentions no parameters at all, failing to compensate for this gap. It doesn't explain what 'region_name', 'period', or authentication parameters like 'profile_name' do, leaving the agent guessing about their purpose and usage.

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: 'Find DynamoDB tables with high capacity utilization (>80%).' It specifies the verb ('Find'), resource ('DynamoDB tables'), and threshold criterion ('>80%'). However, it doesn't explicitly differentiate from sibling tools like 'find_underutilized_dynamodb_tables' or 'analyze_dynamodb_throttling', which would require a 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. It doesn't mention sibling tools like 'find_underutilized_dynamodb_tables' for low utilization or 'analyze_dynamodb_throttling' for performance issues, nor does it specify prerequisites or exclusions. This leaves the agent without context 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool 'Find[s] EC2 instances' and describes the return format ('Dictionary with overutilized EC2 instances'), but lacks details on permissions needed, rate limits, whether it's read-only or destructive, or how it handles errors. The description adds basic context but misses critical behavioral traits for an AWS 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 well-structured and front-loaded with the core purpose, followed by organized sections for arguments and returns. It uses bullet-like formatting for parameters, which aids readability. However, it could be slightly more concise by integrating some parameter details more tightly, and the sentence structure is straightforward but not overly verbose.

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 complexity (8 parameters, no annotations, but has an output schema), the description is fairly complete. It covers the purpose, parameters, and return format, and the output schema likely details the return structure, reducing the need for more in the description. However, it lacks behavioral context like authentication requirements or error handling, which would enhance completeness for an AWS 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 description provides detailed parameter information beyond the input schema, which has 0% schema description coverage. It explains each parameter's purpose (e.g., 'AWS region name', 'Lookback period in days', 'Maximum results to return'), including defaults and optional status. This compensates well for the schema's lack of descriptions, though it doesn't cover all nuances like parameter interactions or validation 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 clearly states the tool's purpose with specific verbs ('Find EC2 instances') and resource ('EC2 instances'), including the exact criteria ('high CPU or memory utilization (≥80%)'). It distinguishes from siblings like 'find_underutilized_ec2_instances' by focusing on overutilization rather than underutilization, making the distinction explicit.

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

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

The description implies usage context through the mention of 'high CPU or memory utilization (≥80%)' and the lookback period, suggesting it's for performance monitoring. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., 'find_underutilized_ec2_instances' or other analysis tools), nor does it specify prerequisites or exclusions, leaving usage somewhat inferred.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the threshold (>80%), it doesn't describe what 'high utilization' means operationally, how the data is collected (e.g., CloudWatch metrics), time aggregation methods, whether this requires specific IAM permissions, or what the output format looks like. For a monitoring/analysis tool with zero 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 extremely concise (one sentence) and front-loaded with the core purpose. Every word earns its place, and there's no wasted text. It efficiently communicates the essential function without unnecessary elaboration.

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 (7 parameters, no annotations, but has output schema), the description is incomplete. While the output schema might cover return values, the description doesn't explain authentication requirements, data source, metric collection methodology, or parameter meanings. For a tool that likely requires AWS credentials and specific permissions, this leaves critical gaps for an AI 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?

The description provides zero information about any of the 7 parameters. With 0% schema description coverage, the description fails completely to compensate for the lack of parameter documentation. Parameters like 'profile_name', 'role_arn', and authentication credentials remain completely unexplained in 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 with specific verbs ('Find') and resources ('ElastiCache clusters'), and it distinguishes itself from siblings by specifying the exact condition (>80% CPU or memory utilization). It's not a tautology and provides meaningful differentiation from tools like 'find_underutilized_elasticache_clusters' or general analysis 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 provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, timing considerations, or how it differs from other tools that might analyze ElastiCache clusters. With many sibling tools available, this lack of contextual guidance is a significant gap.

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 full burden and does well by specifying the CPU threshold (≥80%), lookback period concept, and return format. However, it doesn't mention important behavioral aspects like authentication requirements (though parameters hint at it), rate limits, whether this is a read-only operation, or how the tool interacts with AWS APIs.

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 structured and concise: purpose statement first, followed by clearly labeled 'Args' and 'Returns' sections. Every sentence earns its place, with no redundant information. The parameter documentation is organized efficiently with just the essential details for each.

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 complexity (8 parameters, no annotations, but has output schema), the description is quite complete. It covers purpose, all parameters, and return format. However, it could benefit from more behavioral context about AWS authentication flows and performance characteristics. The output schema existence reduces the need to fully document return values.

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 providing clear documentation for all 8 parameters, including their purposes, defaults, and optional status. It adds significant value beyond the bare schema by explaining what each parameter means (e.g., 'Lookback period in days', 'AWS profile name', 'IAM role ARN to assume').

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 specific verb ('Find') and resource ('RDS instances'), including the exact threshold for 'high CPU utilization' (≥80%). It distinguishes itself from sibling tools like 'analyze_rds_performance_insights' and 'find_underutilized_rds_instances' by focusing specifically on overutilization detection.

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 CPU threshold and parameters, but doesn't explicitly state when to use this tool versus alternatives like 'analyze_rds_performance_insights' or 'find_underutilized_rds_instances'. It provides parameter defaults which offer some guidance, but lacks explicit 'when/when-not' statements or sibling tool comparisons.

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 finds public S3 buckets but doesn't describe how it works (e.g., scans all buckets, checks permissions), what it returns (e.g., list of bucket names, details), or any constraints (e.g., rate limits, authentication requirements). For a tool with 6 parameters related to AWS authentication, this is inadequate.

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—a single sentence with no wasted words. It's front-loaded with the core purpose, making it easy to scan. Every word earns its place by specifying the action, resource, and condition.

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 (6 authentication parameters, no annotations, but an output schema exists), the description is incomplete. It doesn't address authentication needs, explain the tool's scope (e.g., all buckets in an account), or hint at the output format. While the output schema may cover return values, the description fails to provide essential context for a tool interacting with AWS resources.

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 0%, meaning none of the 6 parameters are documented in the schema. The description adds no information about parameters, failing to compensate for this gap. It doesn't explain what 'region_name', 'profile_name', or other authentication parameters mean or how they affect the tool's behavior, leaving them entirely undocumented.

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: 'Find S3 buckets with public access enabled.' It specifies the verb ('Find') and resource ('S3 buckets'), and the condition ('with public access enabled'). However, it doesn't explicitly differentiate from sibling tools like 'find_unencrypted_s3_buckets' or 'find_unused_s3_buckets', which also operate on S3 buckets but for different purposes.

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 prerequisites (e.g., AWS credentials), context (e.g., security auditing), or exclusions (e.g., when to use other 'find' tools for S3 buckets). With many sibling tools focused on AWS resource analysis, this lack of differentiation is a significant gap.

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 that the tool 'finds' target groups, implying a read-only operation, but lacks details on permissions required, rate limits, whether it performs destructive actions, or how it interacts with AWS services. The description is minimal and does not compensate for the absence of 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 well-structured with a clear purpose statement followed by parameter explanations and return information. It is appropriately sized, with no redundant sentences, though it could be slightly more concise by integrating the purpose with the parameter list more seamlessly.

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 complexity (8 parameters, no annotations, but with an output schema), the description is reasonably complete. It explains the purpose, parameters, and return value, though it lacks behavioral context like error handling or performance considerations. The output schema reduces the need to detail return values, but more guidance on usage and behavior would enhance completeness.

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

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

The description includes an 'Args' section that clearly explains each parameter's purpose, such as 'region_name: AWS region name' and 'period: Lookback period in days (default: 7).' This adds significant meaning beyond the input schema, which has 0% description coverage, fully compensating for the schema's lack of parameter details.

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: 'Find target groups with high error rates (5XX errors).' It specifies the verb ('find'), resource ('target groups'), and scope ('with high error rates'), distinguishing it from sibling tools like 'find_target_groups_with_high_response_time' by focusing on error rates rather than response times.

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 does not mention sibling tools, prerequisites, or specific contexts for application, leaving the agent without usage direction beyond the basic purpose.

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 'Find[s] target groups with high response times' and describes the return as a 'Dictionary with target groups having high response times,' but lacks critical details: it doesn't specify what 'high' means beyond the threshold parameter, whether this is a read-only operation (implied but not stated), how results are structured, or any rate limits or authentication requirements beyond the optional credential parameters. For a tool with 8 parameters and 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 well-structured and appropriately sized: a clear purpose statement followed by 'Args' and 'Returns' sections. Each sentence earns its place by explaining parameters and output. However, the 'Args' section is somewhat verbose due to listing all parameters individually, though this is necessary given the 0% schema coverage. It could be more front-loaded with usage context.

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 (8 parameters, no annotations, output schema exists), the description is partially complete. It covers parameters well and notes the return type, but lacks behavioral context (e.g., safety, performance impact) and usage guidelines. The output schema existence means it doesn't need to detail return values, but overall, it's adequate with clear gaps for a tool of this scope.

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 must compensate. It provides a clear 'Args' section listing all 8 parameters with brief explanations (e.g., 'AWS region name,' 'Lookback period in days'), including defaults for 'period' and 'response_time_threshold.' This adds significant meaning beyond the schema's titles, though it doesn't detail constraints (e.g., valid region formats) or interactions between optional credential parameters. With 0% schema coverage, this is strong but not exhaustive.

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: 'Find target groups with high response times.' It specifies the verb ('Find') and resource ('target groups'), and distinguishes itself from sibling tools like 'find_target_groups_with_high_error_rate' by focusing on response time rather than error rate. However, it doesn't explicitly differentiate from other performance analysis tools in the list, such as 'analyze_api_gateway_performance' or 'analyze_rds_performance_insights', which slightly reduces specificity.

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 prerequisites (e.g., AWS permissions), context (e.g., performance troubleshooting), or exclusions (e.g., when to use other tools like 'find_target_groups_with_high_error_rate'). The agent must infer usage from the tool name and sibling list 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 finds tables but doesn't explain how it determines 'low capacity utilization' (e.g., thresholds, metrics like read/write capacity), what the output includes (though an output schema exists), whether it requires specific AWS permissions, or if it has side effects like API rate limits. For a tool with 7 parameters and no annotations, 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, clear sentence: 'Find DynamoDB tables with low capacity utilization.' It is front-loaded with the core purpose, has zero redundant words, and efficiently communicates the essential action without unnecessary elaboration. This is an example of optimal conciseness.

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 (7 parameters, no annotations, schema coverage 0%) and the presence of an output schema, the description is incomplete. It doesn't address parameter meanings, behavioral details like how 'low utilization' is defined, or usage context. While the output schema may cover return values, the description fails to provide enough context for effective tool selection and invocation, especially compared to richer sibling tools in the list.

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 0%, meaning none of the 7 parameters have descriptions in the schema. The tool description adds no parameter information beyond what's implied by the tool name (e.g., it doesn't explain what 'region_name', 'period', or authentication parameters like 'profile_name' are used for). With 7 undocumented parameters and no compensation in the description, this is inadequate for understanding 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's purpose: 'Find DynamoDB tables with low capacity utilization.' It specifies the verb ('Find') and resource ('DynamoDB tables') with a specific criterion ('low capacity utilization'). However, it doesn't explicitly differentiate from sibling tools like 'find_overutilized_dynamodb_tables' or 'find_unused_dynamodb_tables', which would require mentioning contrasting conditions (e.g., 'low' vs. 'high' or 'underutilized' vs. 'unused').

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 like 'find_overutilized_dynamodb_tables' or 'find_unused_dynamodb_tables', nor does it specify prerequisites, context (e.g., cost optimization scenarios), or exclusions. The agent must infer usage from the tool name alone, which is insufficient for clear decision-making.

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 must fully disclose behavioral traits. It states the tool 'finds' instances and returns a dictionary, implying a read-only operation, but does not clarify authentication requirements, rate limits, or data sources (e.g., CloudWatch metrics). The mention of AWS credentials parameters hints at authentication needs, but explicit behavioral details like permissions or side effects are missing, leaving gaps for a tool with 8 parameters.

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 well-structured and appropriately sized. It starts with the core purpose, followed by a clear 'Args' section listing parameters with brief explanations, and ends with return information. Every sentence adds value, though the parameter list is lengthy due to the tool's complexity; it remains front-loaded and efficient without unnecessary verbosity.

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 complexity (8 parameters, no annotations, but with an output schema), the description is partially complete. It covers the purpose and parameters well, and the output schema handles return values, but it lacks behavioral context like authentication details or performance considerations. For a tool with many parameters and no annotations, more guidance on usage and constraints would enhance completeness.

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

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

The description adds significant semantic value beyond the input schema, which has 0% description coverage. It explains each parameter's purpose (e.g., 'AWS region name', 'Lookback period in days', 'AWS profile name'), including defaults and optionality. This compensates fully for the schema's lack of descriptions, making parameter meanings clear and actionable for the agent.

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: 'Find EC2 instances with low CPU and memory utilization (≤20%).' It specifies the verb ('find'), resource ('EC2 instances'), and criteria ('low CPU and memory utilization ≤20%'). This distinguishes it from sibling tools like 'find_overutilized_ec2_instances' and other analysis tools, making the purpose specific and unambiguous.

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. While it mentions the criteria (low CPU/memory ≤20%), it does not specify use cases, prerequisites, or exclusions. Given the many sibling tools for cost optimization and resource analysis, the lack of contextual guidance leaves the agent to infer usage scenarios independently.

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 finds services with low utilization but doesn't describe how it works (e.g., uses CloudWatch metrics, scans all services in a region), what it returns (e.g., list of service ARNs, utilization percentages), or any side effects (e.g., read-only, requires permissions). For a tool with 7 parameters and no annotations, this is inadequate.

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 directly states the tool's purpose without unnecessary words. It's appropriately sized for a simple find operation, though it could benefit from additional context given the complexity implied by the parameters.

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 has 7 parameters with 0% schema coverage, no annotations, and an output schema (which helps but isn't described), the description is incomplete. It doesn't explain parameter roles, authentication needs, how the 20% threshold is applied, or what the output contains. For a tool that likely interacts with AWS ECS and CloudWatch, more context is needed for effective 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 description coverage is 0%, meaning none of the 7 parameters have descriptions in the schema. The tool description provides no information about any parameters—it doesn't mention region, period, authentication fields (profile_name, role_arn, access_key, etc.), or how they affect the search. This leaves all parameters undocumented, which is a critical gap.

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: 'Find ECS services with low CPU and memory utilization (<20%).' It specifies the verb ('Find'), resource ('ECS services'), and criteria ('low CPU and memory utilization <20%'). However, it doesn't explicitly differentiate from sibling tools like 'find_underutilized_ec2_instances' or 'find_unused_ecs_clusters_and_services' beyond the resource type.

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 prerequisites (e.g., AWS credentials setup), timing considerations, or how it differs from other 'find_underutilized_' or 'find_unused_' tools in the sibling list. The agent must infer usage from the name and 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool finds clusters with low CPU utilization but fails to describe key behaviors: whether it's a read-only operation, how it handles authentication (implied by parameters but not stated), potential rate limits, or what the output includes (though an output schema exists). This leaves significant gaps for an AI agent.

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 directly states the tool's purpose without unnecessary words. It is front-loaded with the core functionality, making it easy for an AI agent to quickly understand what the tool does.

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 7 parameters with 0% schema coverage and no annotations, the description is insufficient. It covers the basic purpose but lacks details on parameter usage, behavioral traits, and authentication context. While an output schema exists, the description does not provide enough guidance for effective tool invocation in a real-world scenario.

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 no information about any of the 7 parameters, which have 0% schema description coverage. It does not explain what 'region_name', 'period', or authentication parameters like 'profile_name' mean in context, nor how they affect the search. This fails to compensate for the lack of schema descriptions, leaving parameters largely undocumented.

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 ('find') and resource ('ElastiCache clusters'), and includes a precise criterion ('low CPU utilization (<20%)'). It effectively distinguishes this tool from its sibling 'find_overutilized_elasticache_clusters' by focusing on underutilization rather than overutilization.

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 other underutilized resource tools (e.g., 'find_underutilized_ec2_instances') or related tools like 'find_overutilized_elasticache_clusters'. It lacks context about prerequisites, typical use cases, or exclusions, offering only the basic functionality.

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 what the tool finds but doesn't explain how it works—e.g., whether it requires specific AWS permissions, how it determines 'low' or 'high' thresholds, if it's read-only or modifies data, or what the output looks like. For a tool with 7 parameters and no annotations, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded with the core functionality, making it easy to parse quickly. Every word earns its place, achieving ideal conciseness.

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 complexity (7 parameters, no annotations, but with an output schema), the description is incomplete. It doesn't address parameter meanings, behavioral traits like authentication needs or rate limits, or how it interacts with sibling tools. While the output schema might cover return values, the description lacks essential context for effective tool selection and 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 description coverage is 0%, meaning none of the 7 parameters have descriptions in the schema. The tool description doesn't mention any parameters, leaving all of them undocumented. While it implies criteria like 'period' might relate to the analysis timeframe, it doesn't explain parameter roles, defaults, or interactions, failing to compensate for the schema's lack of coverage.

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: 'Find Lambda functions with low invocation rates or high error rates.' It specifies the verb ('Find'), resource ('Lambda functions'), and criteria ('low invocation rates or high error rates'), making it easy to understand what the tool does. However, it doesn't explicitly differentiate from sibling tools like 'find_unused_lambda_functions' or 'analyze_lambda_cold_starts', which prevents 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 many sibling tools focused on Lambda optimization (e.g., 'find_unused_lambda_functions', 'analyze_lambda_cold_starts'), there's no indication of how this tool's focus on underutilization differs or when it's most appropriate. This leaves the agent guessing about context 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool returns a dictionary but doesn't describe the structure, format, or keys of the output. It also doesn't disclose authentication requirements, rate limits, side effects, or error handling. The description adds minimal behavioral context beyond the basic purpose.

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 well-structured with a clear purpose statement followed by organized 'Args' and 'Returns' sections. It's appropriately sized for an 8-parameter tool, though the AWS credential parameters could be grouped conceptually. Every sentence adds value, with no redundant 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 complexity (8 parameters, no annotations, but with output schema), the description is moderately complete. It explains parameters well and mentions the return type, but lacks behavioral context like authentication needs or performance characteristics. The output schema existence reduces the need to detail return values, but more operational guidance would help.

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 provides detailed parameter semantics in the 'Args' section, explaining each parameter's purpose (e.g., 'AWS region name', 'Lookback period in days'). Since schema description coverage is 0%, the description fully compensates by adding meaning beyond the schema's titles, clarifying defaults and optionality for all 8 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: 'Find RDS instances with low CPU utilization (≤20%)'. It specifies the verb ('Find'), resource ('RDS instances'), and the exact criterion ('low CPU utilization ≤20%'). This distinguishes it from sibling tools like 'find_overutilized_rds_instances' and 'analyze_rds_performance_insights'.

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 like 'find_overutilized_rds_instances' or 'analyze_rds_performance_insights', nor does it specify prerequisites, typical use cases, or exclusions. The agent must infer usage from the purpose 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. The description only states what the tool does ('Find'), not how it behaves. It doesn't mention whether this is a read-only operation, what permissions are required, whether it scans all regions or just one, what format the output takes, or any rate limits. For a tool with 6 parameters and no annotation coverage, this is inadequate.

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, clear sentence with zero wasted words. It's appropriately sized for a simple tool and front-loads the core purpose immediately. 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?

Given the tool's complexity (6 parameters, no annotations, but with an output schema), the description is incomplete. While the output schema may cover return values, the description doesn't address authentication needs, regional scoping, or behavioral traits. For a security-focused tool that likely requires specific AWS permissions and has operational implications, this minimal description leaves significant 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?

Schema description coverage is 0%, meaning none of the 6 parameters have descriptions in the schema. The tool description adds no information about any parameters—it doesn't mention region selection, authentication methods (profile, role, keys), or how these affect the operation. The description fails to compensate for the complete lack of schema 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 tool's purpose: 'Find EBS volumes without encryption enabled.' It specifies the verb ('Find') and resource ('EBS volumes') with a specific condition ('without encryption enabled'). However, it doesn't explicitly differentiate from sibling tools like 'find_unencrypted_rds_instances' or 'find_unencrypted_s3_buckets' beyond the resource type, which prevents 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. There are many sibling tools for finding various AWS resources, but no indication of whether this is for security audits, compliance checks, or cost optimization. The agent must infer usage from the tool name 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 'finds' instances, implying a read-only operation, but doesn't clarify if it requires specific AWS permissions, whether it's safe to run (e.g., no side effects), or what the output format is. For a security-focused tool with zero annotation coverage, this is inadequate.

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, clear sentence with zero waste: 'Find RDS instances without encryption enabled.' It's appropriately sized and front-loaded, making it easy to understand at a glance without unnecessary elaboration.

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 (security tool with AWS integration), lack of annotations, and 0% schema coverage, the description is incomplete. However, an output schema exists, which may document return values, reducing the burden on the description. The description covers the core purpose but misses critical context like parameter usage, behavioral traits, and guidelines.

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 0%, meaning none of the 6 parameters are documented in the schema. The description adds no information about parameters, failing to compensate for this gap. It doesn't explain what 'region_name', 'profile_name', or other AWS credential parameters mean or how they affect the tool's behavior, leaving them entirely unexplained.

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: 'Find RDS instances without encryption enabled.' It specifies the verb ('Find'), resource ('RDS instances'), and criteria ('without encryption enabled'), which is clear and specific. However, it doesn't explicitly distinguish itself from sibling tools like 'find_unencrypted_ebs_volumes' or 'find_unencrypted_s3_buckets' beyond the resource type, which prevents 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. It doesn't mention prerequisites (e.g., AWS credentials), context (e.g., security audits), or exclusions (e.g., what types of RDS instances are excluded). With many sibling tools for cost optimization and security analysis, this lack of differentiation is a significant gap.

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 full burden for behavioral disclosure. It states what the tool does but doesn't describe how it behaves: no information about authentication requirements (though parameters suggest AWS auth), rate limits, whether it's read-only or destructive, what the output looks like, or any side effects. The description is minimal and lacks operational context.

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 at one sentence with no wasted words. It's front-loaded with the core purpose and doesn't include unnecessary elaboration. Every word earns its place in communicating the essential function.

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 complexity (6 parameters, AWS authentication), lack of annotations, and 0% schema description coverage, the description is incomplete. While an output schema exists (per context signals), the description doesn't provide enough context about authentication, scope, limitations, or how results are returned. For a security scanning tool with multiple auth parameters, more guidance is needed.

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 provides no information about parameters, while the schema has 6 parameters with 0% description coverage. Parameters like 'region_name', 'profile_name', 'role_arn', and authentication keys are completely undocumented in both schema and description. The description doesn't compensate for the schema's lack of 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 tool's purpose: 'Find S3 buckets without default encryption enabled.' It specifies the verb ('find') and resource ('S3 buckets') with a specific condition ('without default encryption enabled'). However, it doesn't explicitly differentiate from sibling tools like 'find_public_s3_buckets' or 'find_unused_s3_buckets' that also target S3 buckets with different 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 no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'find_public_s3_buckets' or 'find_unused_s3_buckets' that might be relevant for different S3 security or optimization scenarios. There's no context about prerequisites, timing, or exclusions.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool finds resources but doesn't mention what types of resources it covers, whether it's a read-only operation, if it requires specific AWS permissions, how results are returned, or any rate limits. For a tool with 7 parameters and no annotations, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy for an agent 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 complexity (7 parameters, no annotations, but an output schema exists), the description is incomplete. While the output schema may handle return values, the description doesn't address key aspects like resource scope, authentication requirements, or behavioral traits. For a tool with multiple parameters and no annotations, more context is needed to guide effective 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?

The description adds no information about parameters beyond what's in the schema. With 7 parameters and 0% schema description coverage, the schema only provides titles and types. The description doesn't explain what 'required_tags' should contain, how 'region_name' affects the search, or the purpose of authentication parameters like 'profile_name' and 'role_arn'. This fails to compensate for the low schema coverage.

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: 'Find AWS resources missing required tags.' It specifies the verb ('Find'), resource type ('AWS resources'), and condition ('missing required tags'). However, it doesn't explicitly differentiate from sibling tools like 'analyze_tag_compliance' or other 'find_' tools, which prevents 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 many sibling tools focused on AWS resource analysis (e.g., 'analyze_tag_compliance', 'find_public_s3_buckets'), there's no indication of context, prerequisites, or comparisons. This leaves the agent to infer usage based on the name 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. It discloses the tool's read-only nature by implying it 'finds' unused AMIs without modifying them, but lacks details on permissions, rate limits, or error handling. The description adds some context but is incomplete for a tool with 8 parameters.

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 well-structured and appropriately sized, with a purpose statement followed by 'Args' and 'Returns' sections. It avoids redundancy, though the parameter list is lengthy due to the high parameter count, which is necessary for clarity.

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 complexity (8 parameters, no annotations, but has an output schema), the description is mostly complete. It covers purpose, parameters, and return type, though it could improve by adding usage guidelines or behavioral details like authentication requirements.

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 listing all 8 parameters with clear semantics, including defaults and optionality (e.g., 'period: Minimum age in days for AMI to be considered unused (default: 90)'). It adds meaning beyond the bare schema, making parameters understandable.

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 ('Find') and resource ('AMIs not used by any EC2 instances, ASGs, or Spot Fleet Requests'), distinguishing it from siblings like 'find_unused_cloudwatch_alarms' or 'find_unused_s3_buckets' by focusing on AMIs and their usage status.

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 other 'find_unused_' tools for different resources or cost analysis tools. It lacks explicit context, exclusions, or prerequisites, offering only the basic functionality.

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 what the tool does but lacks details on permissions required, whether it's read-only or destructive, rate limits, output format, or error handling. For a tool with 7 parameters and AWS authentication inputs, this is a significant 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, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to understand at a glance.

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 complexity (7 parameters, AWS authentication, no annotations) and the presence of an output schema, the description is insufficient. It doesn't address authentication requirements, what 'unused' means operationally, or how results are returned. The output schema existence helps, but the description should provide more context for proper tool selection and 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?

The description mentions 'specified period' which maps to the 'period' parameter, but with 0% schema description coverage and 7 total parameters (including authentication fields like profile_name, role_arn, access_key), it fails to add meaningful context beyond what's implied. The schema titles provide basic labels, but the description doesn't explain parameter purposes or relationships.

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 ('Find') and resource ('CloudFront distributions') with a precise condition ('with no requests in the specified period'). It distinguishes from siblings like 'find_unused_amis' or 'find_unused_s3_buckets' by specifying the resource type and the 'no requests' criterion.

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

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

No guidance is provided on when to use this tool versus alternatives. While the purpose is clear, there's no mention of prerequisites, typical use cases, or how it differs from other cost-optimization tools in the sibling list. The agent must infer usage 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.