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 returns 'API version information', which implies a read-only operation, but doesn't disclose any behavioral traits like authentication needs, rate limits, error handling, or what the output format entails. This is a significant gap for a tool with no annotation coverage.

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

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

The description is extremely concise and front-loaded: the first sentence states the purpose clearly, and the second briefly notes the return. There is zero wasted text, making it highly efficient and well-structured.

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

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

Given the tool's low complexity (0 parameters, read-only implied) and the presence of an output schema, the description is minimally adequate. However, with no annotations and incomplete behavioral disclosure, it lacks depth for a fully informed agent, scoring at the minimum viable level.

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 no parameter documentation is needed. The description doesn't add parameter details, which is appropriate here, but it does mention the return value, providing some context beyond the schema. Baseline 4 is correct for zero 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 verb 'Get' and the resource 'current Adzuna API version', making the purpose specific and understandable. However, it doesn't explicitly differentiate this tool from its siblings (like get_categories, get_geodata, etc.), which all appear to be read-only data retrieval tools, so it misses the top 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 any context, prerequisites, or exclusions, leaving the agent with no usage instructions 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it's a read-only lookup operation that returns category data. It also provides important context about country-specific tags and includes error handling information (rate limits, authentication failures, invalid inputs). However, it doesn't explicitly mention whether this is a safe operation or if it has side effects.

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

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

The description is well-structured with clear sections (PURPOSE, Args, Returns, Common category tags, Example response, Usage, Errors). However, it's quite lengthy with multiple examples and detailed error information. While informative, some content (like the extensive example response and common category list) could potentially be streamlined.

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 (country-specific data lookup with sibling tool dependencies), the description provides complete context. It explains the tool's purpose, usage guidelines, parameter semantics, return format, and error conditions. The presence of an output schema means the description doesn't need to explain return values in detail, but it still provides helpful examples and context about how to use the returned data.

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 has 0% description coverage, so the description must fully compensate. It provides comprehensive parameter information: explains the 'country' parameter requires ISO 3166-1 alpha-2 codes, lists all 12 supported country codes, and explains the parameter's purpose in relation to the sibling tool. 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 tool's purpose: 'Get valid job category tags for a specific country.' It specifies the verb ('Get'), resource ('valid job category tags'), and scope ('for a specific country'). It also explicitly distinguishes this tool from its sibling 'search_jobs' by stating its purpose is to provide parameter values for that tool.

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

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

The description provides explicit guidance on when to use this tool: 'Use this BEFORE search_jobs to get valid 'category' parameter values.' It also specifies constraints: 'Category tags are COUNTRY-SPECIFIC - always use the same country code here as you will in search_jobs.' This clearly defines the tool's role relative to its sibling and establishes 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 and does an excellent job disclosing behavioral traits. It explains result ordering ('ordered by job count'), data characteristics ('average_salary is ANNUAL in LOCAL CURRENCY'), typical output size ('Typically returns 10-20 top regions'), and comprehensive error handling. The Notes and Errors sections provide crucial operational context that annotations would normally cover.

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 clear sections (PURPOSE, Args, Returns, Example, Notes, Errors) and front-loads the core functionality. While comprehensive, some sections like the detailed example response could be slightly condensed. Every sentence adds value, but the overall length is justified given the tool's complexity and lack of annotations.

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 4 parameters, 0% schema coverage, no annotations, but with output schema, the description is exceptionally complete. It covers purpose, usage, all parameter semantics, return format with detailed example, behavioral notes, and error handling. The output schema existence means the description doesn't need to exhaustively document return structure, but it still provides a helpful example. Nothing essential is missing.

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

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

Given 0% schema description coverage, the description fully compensates by providing rich semantic information for all parameters. It explains country codes with specific supported values, clarifies keywords usage ('Filter to specific roles'), details location behavior with concrete examples (empty vs 'London'), and explains category referencing ('Category tag from get_categories'). The Args section adds substantial 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 tool's purpose with specific verbs ('Get salary and job count data') and resources ('broken down by geographic region'). It distinguishes from sibling tools like get_salary_histogram or search_jobs by focusing on geographic breakdowns rather than salary distributions or job searches. The PURPOSE section reinforces this with concrete use cases like 'Where are the highest paying X jobs?' and 'Which cities have the most opportunities?'

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

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

The description provides clear context for when to use this tool through the PURPOSE section and example questions, but doesn't explicitly state when NOT to use it or name specific alternatives among sibling tools. It implies usage for geographic comparisons but doesn't contrast with tools like get_salary_histogram (which might show salary distributions without geographic breakdown) or search_jobs (which might return individual job listings).

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 and does so effectively. It describes important constraints (only includes jobs with listed salaries), explains how to interpret results (annual salaries in local currency, typical bucket increments), and documents error conditions including rate limits and authentication failures. The only minor gap is it doesn't explicitly state whether this is a read-only operation, though 'Get' implies it is.

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 clear sections (PURPOSE, IMPORTANT, Args, Returns, Example, How to interpret, Errors) and every sentence adds value. While comprehensive, it's appropriately sized for a tool with multiple parameters and complex output interpretation. The only minor improvement would be slightly tighter phrasing in some sections.

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 (4 parameters, histogram output, country-specific behavior) and the presence of an output schema, the description is remarkably complete. It covers purpose, usage guidelines, parameter semantics, output interpretation with examples, and error conditions. The output schema handles the return structure, while the description explains how to interpret the histogram data, creating a comprehensive package.

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 rich semantic information for all parameters. It explains what 'country' controls (currency), lists supported values, clarifies that keywords/location/category are filters with examples, and notes which parameters have null defaults. This goes well beyond what the bare schema provides.

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 ('salary distribution histogram for jobs matching search criteria'). It distinguishes from siblings by focusing specifically on salary histogram data rather than job listings (search_jobs), categories (get_categories), or other data types. The PURPOSE section reinforces this with concrete use cases.

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

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

The description provides explicit guidance on when to use this tool vs alternatives through the IMPORTANT section ('Only includes jobs WITH listed salaries') and by contrasting with sibling tools. The PURPOSE section lists three specific scenarios where this tool is useful, and the description implicitly distinguishes it from search_jobs (which returns job listings rather than aggregated salary data).

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 excels by disclosing critical behavioral traits: rate limits (Error: 'API Error 429'), authentication requirements ('API Error 401'), default values (months default 12), constraints (max ~24 months), and error conditions for invalid inputs. The 'How to analyze' section adds valuable guidance on interpreting results.

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?

Well-structured with clear sections (PURPOSE, Args, Returns, Example, How to analyze, Errors), but slightly verbose at ~200 words. Every section earns its place by adding value, though some redundancy exists between the initial description and PURPOSE section. Front-loading is effective with the core purpose stated immediately.

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?

Exceptionally complete given the complexity: no annotations but the description covers purpose, usage, all parameters, output format (with example), analysis methodology, and error conditions. The output schema exists, so the description appropriately focuses on interpretation rather than re-describing return structure. Nothing essential is missing for a trend analysis 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?

With 0% schema description coverage, the description fully compensates by providing rich semantic context for all 5 parameters: country (ISO codes with supported list), keywords (role filtering examples), location (example), category (reference to get_categories), and months (default, max, and usage guidance for different values). This goes far beyond what the bare schema provides.

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 ('historical salary trends for matching jobs'), distinguishing it from siblings like get_salary_histogram (distribution) or search_jobs (job listings). The PURPOSE section reinforces this with concrete use cases like trend analysis and negotiations.

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

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

The description provides clear context for when to use this tool (analyzing salary trends over time) and includes practical examples like 'Are X salaries going up or down?' However, it doesn't explicitly contrast when to use this versus alternatives like get_salary_histogram or get_top_companies, missing explicit sibling differentiation.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so effectively. It describes key behavioral traits: ranking method ('Ranked by job count'), typical output size ('Typically returns 10-20 companies'), data interpretation ('average_salary is ANNUAL in LOCAL CURRENCY'), and limitations ('Smaller great companies may not appear'). The Errors section also discloses potential API issues including rate limits and authentication requirements, which is valuable context not covered by 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 clear sections (PURPOSE, NOTE, Args, Returns, Example, Notes, Errors) that make information easy to locate. While comprehensive, it maintains efficiency with most sentences adding value. The front-loaded purpose statement is excellent, though some sections could be slightly more concise without losing 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 (4 parameters, no annotations, but has output schema), the description is remarkably complete. It covers purpose, usage guidelines, parameter semantics, behavioral traits, example output, and error conditions. The output schema exists, so the description appropriately focuses on interpreting the return values rather than just documenting structure. This provides all necessary context for an agent to use the 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?

With 0% schema description coverage, the description fully compensates by providing comprehensive parameter semantics. It explains each parameter's purpose: country filtering with supported codes, keywords for role filtering, location for geographic filtering, and category for job category filtering. It provides specific examples and constraints (e.g., 'ISO 3166-1 alpha-2 country code' with supported values), adding significant meaning beyond what the bare schema provides.

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

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

The description clearly states the tool's purpose: 'Get top employers currently hiring, ranked by number of open positions.' It specifies the verb ('get'), resource ('top employers'), and ranking criteria ('by number of open positions'), distinguishing it from sibling tools like search_jobs or get_salary_histogram. The PURPOSE section further elaborates with specific use cases, making the intent 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 clear context for when to use this tool: 'Identify major employers in a field' and 'Useful for' scenarios like researching potential employers or understanding market leaders by hiring volume. It explicitly notes limitations ('Shows hiring VOLUME, not company quality') and distinguishes from alternatives by focusing on ranking rather than detailed job searches. However, it doesn't explicitly state when NOT to use it or directly compare to all sibling 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 the full burden of behavioral disclosure and does so comprehensively. It explains: salary figures are ANNUAL in LOCAL CURRENCY, keywords are OR'd and case-insensitive, location uses fuzzy matching, pagination starts at page 1, salary filters exclude jobs without listed salaries, and it documents specific error conditions (rate limits, authentication failures, invalid inputs). This goes well 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 well-structured with clear sections (Args, Returns, Errors) and uses bullet points effectively. While comprehensive, it's appropriately sized for a complex tool with 14 parameters. Some redundancy exists (salary currency mentioned multiple times), but overall the structure helps navigation. Every sentence adds value, though it could be slightly more concise in places.

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 (14 parameters, no annotations, 0% schema coverage) and the presence of an output schema, the description is remarkably complete. It covers purpose, usage guidelines, detailed parameter semantics, behavioral traits, error conditions, and includes a comprehensive example response. The output schema handles return value structure, allowing the description to focus on semantic context. This provides everything needed for effective tool 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?

With 0% schema description coverage for 14 parameters, the description fully compensates by providing detailed semantic information for every parameter. Each parameter gets clear explanations: country includes supported codes and currency implications, keywords explains OR logic and examples, location describes fuzzy matching and examples, page clarifies starts at 1, salary_min notes exclusion behavior, category references get_categories prerequisite, etc. The description adds substantial 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 tool's purpose: 'Search for jobs on Adzuna across 12 supported countries.' It specifies the verb ('search'), resource ('jobs'), and scope ('across 12 supported countries'), distinguishing it from sibling tools like get_categories or get_top_companies. The description immediately establishes this is a search tool for job listings.

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

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

The description provides explicit guidance on when to use this tool versus alternatives. It mentions: 'For remote jobs, include "remote" in keywords' (instead of using location), 'Call get_categories(country) first to get valid tags' (prerequisite for category parameter), and lists sibling tools like get_categories that should be used first. It also explains when to leave parameters empty (location for country-wide search).

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