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. However, it only states the action generically ('analyze') without explaining what the tool actually does—e.g., whether it runs queries, collects metrics, generates reports, or modifies data. It lacks critical details like permissions needed, side effects, rate limits, or output format, making it inadequate for a tool with 4 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 concise with a single sentence, but it's under-specified rather than efficiently informative. While it avoids unnecessary words, it doesn't front-load key details—the phrase 'with improved efficiency' adds little value and could be replaced with more substantive information. It earns a middle score for brevity but lacks meaningful 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 complexity of a 4-parameter tool with no annotations, 0% schema coverage, and no output schema, the description is severely incomplete. It doesn't explain what the tool analyzes (e.g., CPU, memory, queries), how results are returned, or the purpose of parameters, leaving the agent unable to use the tool correctly. This is inadequate for even basic functionality.

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 4 parameters have descriptions in the schema. The tool description adds no information about what parameters like 'window_minutes', 'bucket', 'top_n', or 'flush' mean or how they affect the analysis. Without this, the agent cannot understand how to use these parameters effectively, failing to compensate for the schema 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 'Analyze system performance with improved efficiency' is vague and tautological. It restates the tool name ('analyze_system_performance') with the generic addition 'with improved efficiency', which doesn't clarify what specific resource or scope is being analyzed. It fails to distinguish this tool from sibling tools like 'database_status' or 'generate_health_dashboard' that might also analyze performance aspects.

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 any context, prerequisites, or exclusions, nor does it reference sibling tools like 'database_status' or 'profile_query' that might be related. This leaves the agent with no information to make an informed choice among performance-related 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 mentions 'improved error handling and formatting,' which adds some context about reliability and output presentation, but fails to specify what 'status' includes (e.g., uptime, connections, performance metrics), whether it requires permissions, or if it's safe to use frequently. This leaves significant gaps for a tool with zero 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 front-loads the core purpose ('Get database status') and adds value with additional context ('with improved error handling and formatting'). There is no wasted verbiage, and every part of the sentence contributes to understanding the tool's 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 tool's complexity (simple, no parameters) and the lack of annotations and output schema, the description is minimally adequate. It states what the tool does and hints at behavioral traits, but doesn't fully compensate for the missing structured data—e.g., it doesn't explain what 'status' entails or the format of the output. This makes it complete enough for basic use but with clear gaps.

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

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

The tool has 0 parameters, and the schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately avoids discussing any. A baseline of 4 is applied since no parameters exist, and the description doesn't mislead about 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 with a specific verb ('Get') and resource ('database status'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'analyze_system_performance' or 'generate_health_dashboard', which might provide overlapping or related functionality.

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 siblings like 'analyze_system_performance' and 'generate_health_dashboard' that might offer similar status or health information, there's no indication of when this specific tool is preferred, nor any prerequisites or exclusions 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'pagination support and result size limits' which gives some context about output behavior, but doesn't address critical aspects like whether this is a read-only operation, what permissions are required, error handling, rate limits, or what the actual return format looks like.

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 efficiently communicates the core functionality. It's front-loaded with the main purpose and wastes no words on 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?

For a query execution tool with 5 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain the query language, result format, error conditions, or how pagination actually works in practice. The mention of 'pagination support' is too vague for proper agent 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?

With 0% schema description coverage and 5 parameters (only 1 required), the description provides no information about any parameters. It doesn't explain what 'query' should contain, what 'limit' and 'offset' control, what 'include_columns' affects, or how 'timeout' works. 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 as 'Execute query with pagination support and result size limits' - a specific verb ('execute') and resource ('query') with key capabilities. However, it doesn't distinguish this from sibling tools like 'execute_query_stream' or 'run_query_safely', which likely have different execution characteristics.

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 siblings like 'execute_query_stream', 'run_query_safely', and 'profile_query' available, there's no indication of when paginated execution is preferred over streaming, safe execution, or profiling approaches.

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 'batching and size limits', which hints at performance characteristics, but fails to describe critical behaviors like whether this is a read-only operation, potential side effects, error handling, authentication requirements, or rate limits. For a query execution tool with zero annotation coverage, this leaves significant 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 extremely concise—a single sentence with zero waste. It's front-loaded with the core purpose and efficiently mentions key features. Every word earns its place, 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 complexity of a query execution tool with 4 parameters, 0% schema description coverage, no annotations, and no output schema, the description is insufficient. It lacks details on return values, error conditions, performance implications, and how it differs from sibling tools. For a tool that likely handles data retrieval with streaming, more context is needed for safe and 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%, so the description must compensate. It mentions 'batching and size limits', which loosely relates to 'batch_size' and 'max_rows' parameters, but doesn't explain the meaning or usage of 'query' or 'timeout'. The description adds some value by hinting at parameter purposes but doesn't fully compensate for the lack of schema descriptions, resulting in a baseline score.

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: 'Stream query results with batching and size limits.' It specifies the verb ('stream') and resource ('query results'), and mentions key operational aspects (batching, size limits). However, it doesn't explicitly differentiate from sibling tools like 'execute_query_paginated' or 'run_query_safely', 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 sibling tools like 'execute_query_paginated' and 'run_query_safely' available, there's no indication of when streaming is preferred over pagination or safe execution, nor any mention of prerequisites or constraints for 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'controlled output,' which hints at some behavioral trait, but doesn't elaborate on what this means (e.g., rate limits, permissions, or side effects). For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves beyond basic functionality.

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

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

The description is front-loaded with the core purpose, followed by structured sections for args and returns. It's efficient with no wasted sentences, though the 'ctx' parameter lacks explanation, which slightly reduces clarity. Overall, it's appropriately sized and well-organized.

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 (generating a dashboard), lack of annotations, no output schema, and incomplete parameter documentation, the description is adequate but has clear gaps. It covers the basic purpose and some parameter details but misses behavioral context and full parameter semantics, making it minimally viable but not fully complete.

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 lists 'output_format' as a parameter with possible values ('compact, detailed, json'), which adds meaning beyond the input schema's 0% coverage. However, it doesn't explain the 'ctx' parameter at all, leaving it undocumented. With 1 parameter total and partial coverage in the description, this meets the baseline for minimal viability but doesn't fully compensate for the schema 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: 'Generate consolidated health dashboard with controlled output.' It specifies the verb ('generate') and resource ('health dashboard'), and the 'consolidated' modifier adds useful context. However, it doesn't explicitly differentiate this from sibling tools like 'analyze_system_performance' or 'database_status', which might offer overlapping functionality.

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, and there's no comparison to sibling tools like 'analyze_system_performance' or 'database_status' that might serve similar purposes. 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. It adds value by disclosing caching behavior, which is a useful trait beyond basic functionality. However, it lacks details on permissions, rate limits, error handling, or what 'List' entails (e.g., format, pagination). For a tool with no annotations, this is a moderate but incomplete disclosure.

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

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

The description is a single, efficient sentence that front-loads the core action ('List database schemas') and adds a key behavioral trait ('with caching') without waste. Every word earns its place, making it highly concise and well-structured.

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

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

Given no annotations, no output schema, and 0 parameters, the description is adequate but has gaps. It covers the basic purpose and a behavioral trait (caching), but for a tool that likely returns a list of schemas, more context on output format or usage scenarios would improve completeness. It's minimally viable but not fully informative.

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 0 parameters with 100% coverage, so the schema fully documents the absence of parameters. The description doesn't need to add parameter details, and it doesn't contradict the schema. A baseline of 4 is appropriate since no parameters exist, and the description doesn't introduce confusion.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('database schemas'), making the purpose specific and understandable. It distinguishes from siblings like get_schema_tables or get_schema_views by focusing on schemas rather than their contents. However, it doesn't explicitly differentiate from all siblings (e.g., database_status might overlap in scope), keeping it from 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 like get_schema_tables or database_status. It mentions caching, which hints at performance considerations, but doesn't specify when caching applies or when to avoid it. Without explicit when/when-not instructions or named alternatives, the score is low.

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 mentions 'with caching', which hints at performance behavior, but doesn't disclose critical traits like whether it's read-only, safe, requires permissions, rate limits, or what the output format looks like. For a tool with 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 extremely concise with a single sentence that front-loads the core action ('List tables in schema') and adds a key detail ('with caching'). There's zero waste or redundancy, making it efficient and 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 complexity (a database query tool with caching), lack of annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't explain return values, error handling, or how caching affects results, leaving the agent with insufficient information to use the tool effectively in 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. It doesn't add any meaning beyond the input schema—no explanation of what 'schema_name' represents, default usage, or how caching interacts with parameters. With 1 parameter undocumented in both schema and description, the description fails to provide necessary 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 clearly states the verb ('List') and resource ('tables in schema'), making the purpose understandable. It distinguishes from siblings like 'get_schema_views' by specifying tables, but doesn't fully differentiate from 'get_table_structure' or 'get_table_projections' which might also involve tables. The mention of 'with caching' adds specificity but doesn't fully clarify uniqueness.

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 when to choose this over 'get_schema_views' for views, 'get_table_structure' for detailed info, or 'execute_query_paginated' for custom queries. There's no context on prerequisites, exclusions, or typical use cases, leaving the agent with minimal 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions caching, which adds some context about performance or data freshness, but fails to cover critical aspects like whether this is a read-only operation, potential side effects, error handling, or rate limits. This leaves significant gaps for a tool that interacts with database schemas.

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 very concise with a single sentence, making it easy to parse. However, it could be more front-loaded by explicitly stating the tool's core function before mentioning caching, but it's still efficient with zero wasted words.

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 database operations, no annotations, no output schema, and low parameter coverage, the description is incomplete. It lacks details on return values, error conditions, caching implications, and how it differs from sibling tools, making it inadequate for safe and effective use by 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 input schema has 1 parameter with 0% description coverage, meaning the schema provides no semantic details. The description adds no information about the 'schema_name' parameter, such as what it represents, valid values, or default behavior beyond the schema's default. 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 with a specific verb ('List') and resource ('views in schema'), making it easy to understand what the tool does. However, it doesn't explicitly differentiate from sibling tools like 'get_schema_tables' or 'get_table_structure', 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 like 'get_schema_tables' or 'get_database_schemas'. It mentions caching but doesn't explain when this is beneficial or if there are trade-offs, leaving the agent with minimal usage context.

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 'List projections for a table,' which implies a read-only operation, but doesn't disclose any behavioral traits such as permissions required, rate limits, whether it returns all projections or a subset, or how it handles errors. This leaves significant gaps for an agent to understand the tool's 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: 'List projections for a table.' It's front-loaded with the core action and target, with zero wasted words. This is appropriately sized for the tool's apparent simplicity, 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 complexity (a read operation with 2 parameters), lack of annotations, 0% schema description coverage, and no output schema, the description is incomplete. It doesn't explain what 'projections' are, the return format, or any behavioral context. For a tool that might involve database-specific concepts, this leaves too many unknowns 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?

The description adds no meaning beyond the input schema, which has 0% schema description coverage. It doesn't explain what 'projections' are or how the parameters relate to them (e.g., if table_name refers to a specific database table). With two parameters (table_name and schema_name) and no schema descriptions, the description fails to compensate, leaving parameters semantically unclear.

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 'List projections for a table' clearly states the action (list) and target (projections for a table), but it's vague about what 'projections' means in this context (e.g., column subsets, materialized views, or database-specific structures). It doesn't differentiate from siblings like get_table_structure or get_schema_tables, which might overlap in scope. This provides a basic purpose but lacks 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?

No guidance is provided on when to use this tool versus alternatives. For example, it doesn't specify if this is for metadata retrieval, performance analysis, or how it differs from siblings like get_table_structure or execute_query_paginated. The description implies usage for listing projections but offers no context on prerequisites, typical scenarios, 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 mentions 'caching support,' which hints at performance optimization, but fails to describe key traits such as whether this is a read-only operation, potential side effects, error handling, or how caching works (e.g., cache duration, invalidation). This leaves significant gaps in understanding the tool's 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 extremely concise with a single sentence, 'Get table structure with caching support,' which is front-loaded and wastes no words. Every part of the sentence contributes to the tool's purpose, making it efficient and easy to parse, though it may be overly brief 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 complexity of a database tool with 2 parameters, no annotations, and no output schema, the description is incomplete. It lacks details on what 'table structure' includes, how caching operates, error conditions, or return values. For a tool that likely returns metadata, this minimal description does not provide enough context 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?

The input schema has 0% description coverage, and the tool description does not add any meaning to the parameters 'table_name' and 'schema_name.' It does not explain what these parameters represent, their expected formats, or how they affect the output. With low schema coverage, the description 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 'Get table structure with caching support,' which includes a verb ('Get') and resource ('table structure'), making it clear what it does at a basic level. However, it lacks specificity about what 'table structure' entails (e.g., columns, data types, constraints) and does not differentiate it from sibling tools like 'get_schema_tables' or 'get_table_projections,' leaving room for ambiguity.

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 mentions 'caching support' but does not explain when caching is beneficial or when to choose this over other tools like 'get_schema_tables' or 'execute_query_paginated' for similar purposes. There is no explicit mention of prerequisites, exclusions, or recommended contexts.

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 'improved error handling', which hints at robustness, but doesn't specify what errors are handled, how they're reported, or any other behavioral traits like performance impact, side effects, or output format. For a tool with no annotations, this is insufficient to inform the agent about its operational characteristics.

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 concise with a single sentence, 'Profile query execution with improved error handling.' It's front-loaded and wastes no words, making it efficient to parse. However, it's under-specified rather than optimally concise, as it lacks necessary details 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 complexity (a query profiling tool with 2 parameters), no annotations, no output schema, and 0% schema coverage, the description is incomplete. It doesn't explain what profiling entails (e.g., returns performance metrics, logs), how errors are handled, or the tool's role among siblings. For a tool that likely involves system interaction, 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?

Schema description coverage is 0%, so the schema provides no parameter descriptions. The tool description adds no information about parameters beyond what's in the schema (e.g., 'query' and 'timeout'). It doesn't explain what a 'query' entails (e.g., SQL, API call), what 'timeout' units are, or default behaviors. With 2 parameters and 0% coverage, the description fails to compensate for the 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 'Profile query execution with improved error handling' states a vague purpose but lacks specificity. It mentions 'profile query execution' which suggests analyzing query performance, but doesn't specify what resource is being profiled (e.g., database queries, system performance). It doesn't clearly distinguish from sibling tools like 'execute_query_paginated' or 'run_query_safely' which might also handle queries. The description is better than a tautology but remains ambiguous about scope.

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 siblings like 'execute_query_paginated', 'execute_query_stream', and 'run_query_safely', the description doesn't explain when profiling is preferred over execution, or what 'improved error handling' entails compared to other tools. This leaves the agent without clear direction on tool selection in context.

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 safety features like size detection, pagination, and timeout support, which adds some context. However, it doesn't detail critical behaviors such as what happens when thresholds are exceeded, how pagination works in practice, or error handling for timeouts, leaving significant 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 appropriately sized with a clear summary sentence followed by a structured parameter list. Each parameter explanation is brief and focused, though the initial summary could be more front-loaded with key usage context. There's minimal wasted text, making it efficient for an agent to parse.

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

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

Given the tool's complexity (8 parameters, no annotations, no output schema), the description is moderately complete. It covers parameter semantics well but lacks behavioral details like response format, error conditions, and sibling differentiation. For a safe query execution tool with many options, more context on outcomes and trade-offs would be beneficial.

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

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

Schema description coverage is 0%, so the description must compensate. It provides a helpful list of all 8 parameters with brief explanations that add meaning beyond the schema's titles and types. For example, it clarifies 'row_threshold' as 'Maximum rows before requiring confirmation' and 'precount' as 'Count total rows for large results (expensive)', which significantly enhances understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool executes SQL queries with safety features like size detection, pagination, and timeout support. It specifies the verb ('execute') and resource ('SQL query') but doesn't explicitly differentiate from siblings like 'execute_query_paginated' or 'execute_query_stream' beyond the 'safely' aspect in the name.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'execute_query_paginated' or 'execute_query_stream'. It mentions features like pagination and streaming modes but doesn't specify scenarios where this tool is preferred over its siblings, leaving the agent to infer usage from parameter names alone.

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