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

With no annotations provided, the description carries the full burden. It implies a read-only operation via 'Get' and adds the debugging context, but it does not disclose what exactly is returned (e.g., version number format) or whether it incurs rate limits. Acceptable but not rich.

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?

A single, front-loaded sentence delivers all essential information with no filler. It names the action, the target resource, and the practical use case efficiently.

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 zero-parameter, no-output-schema tool, the description is sufficient: it states what the tool does and why to use it. It could be improved by specifying the expected return value (e.g., version string), but overall it is complete enough for its simplicity.

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 zero parameters, so schema coverage is effectively 100%. No parameter documentation is needed, and the description does not attempt to add irrelevant detail. Baseline of 4 is appropriate.

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

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

The description clearly states the tool's function with a specific verb ('Get') and resource ('current Adzuna API version'). It stands apart from sibling data-retrieval tools by identifying itself as a meta/debugging endpoint.

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 notes the tool is 'useful for debugging connectivity/auth', providing clear usage context. It does not explicitly mention alternatives, but none of the sibling tools serve this purpose, so this guidance is adequate.

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, the description carries the burden of behavioral disclosure. It provides useful behavioral details: returned keys are 'YYYY-MM' strings and 'order is not guaranteed by the API.' It also clarifies parameter semantics (e.g., country codes, hierarchical location paths). It does not mention rate limits, error behavior, or currency, but for a read-only query tool the disclosed information is substantive.

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 and well-structured: a one-sentence purpose, followed by the return-key behavior, then a compact parameter list. Every sentence adds value, and the most important information is front-loaded.

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 4-parameter tool with no output schema and no annotations, the description covers the essential aspects: purpose, parameter formats, return-key format, and how to discover valid values via regional_data. However, it does not describe the value type/currency of the salaries or any error/missing-data behavior, which would make it 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?

Schema description coverage is 0%, so the description fully compensates by explaining each parameter with types, examples, and source references: 'country: ISO country code, e.g. "gb", "us", "de"', 'category: a category tag as returned by list_categories', 'months: how many months of history to return', and 'location: a hierarchical place, most general first, e.g. ["UK", "London"]'. This adds significant meaning beyond the raw schema.

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

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

The description opens with a specific verb and resource: 'Get average salary by month for a category and/or location, over time.' It clearly defines the tool's scope and differentiates it from siblings like salary_histogram (which likely provides a distribution, not time series) and regional_data (which is for discovering regions, not salary history).

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 on what the tool does and how filters work, and it references sibling tools: 'category: a category tag as returned by list_categories' and 'See regional_data for how to discover valid values.' It does not explicitly state when NOT to use this tool versus salary_histogram or other siblings, but the purpose is clear enough to infer appropriate 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, the description carries the full burden. It implies a read-only listing operation via the verb 'list' and gives examples of the returned tags, but does not explicitly disclose auth requirements, rate limits, or handling of invalid country codes. This is adequate but not rich.

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 compact and front-loaded: two sentences state the purpose and parameter format, and one sentence explains downstream usage. Every sentence earns its place with no 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?

Despite lacking an output schema, the description is complete for this simple tool. It covers purpose, parameter semantics, and how the results integrate with five sibling tools, making it clear what the agent can expect and how to use the response.

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 for the only parameter 'country' provides just its name and type. The description compensates by specifying the ISO country code format and giving concrete examples like 'gb', 'us', 'de', thereby adding significant meaning beyond the schema.

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

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

The description clearly states the tool lists job category tags for a country, with examples like 'it-jobs' and 'sales-jobs'. It distinguishes itself from sibling tools by being the source for category tags used by various search and aggregation 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 explains that the returned tags can be passed as the `category` param to search_jobs, salary_histogram, top_companies, regional_data, and historical_salary, giving clear context for when to use this tool. It doesn't explicitly say when not to use it, but the consumer relationships are clear.

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, the description carries the burden of behavioral disclosure. It reveals that each returned location includes an `area` array to reuse verbatim and explains the effect of omitting `location`. It doesn't mention output shape beyond that or any limitations, but it's sufficient for a simple read-only retrieval 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?

Purpose is front-loaded in the first sentence, followed by a practical note and compact parameter descriptions. Every sentence adds value, with no filler.

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

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

The description covers the core functionality, parameter semantics, and a bonus usage tip. It doesn't elaborate on the full response format or possible error conditions, but for a straightforward regional-data tool, it's adequately 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?

All three parameters are explained beyond the bare schema: `country` gets ISO examples, `category` is tied to `list_categories`, and `location` is described as hierarchical with an example and behavior when omitted. This fully compensates for the 0% schema description 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?

States exactly what it does with a specific verb and resource: 'Get vacancy counts for each sub-region of a given location.' Also distinguishes itself from siblings by focusing on regional breakdowns and adding a secondary purpose of discovering reusable `area` strings for other 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?

Provides clear usage context: when you need sub-regional vacancy counts or exact `area` strings for the `location` param on other tools. It also explains that omitting `location` gives top-level regions, but it doesn't explicitly contrast with sibling tools or state when not to use it.

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

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

With no annotations, the description carries the full burden. It explains the return format (keys are lower bounds, values are vacancy counts) and parameter semantics including AND logic. However, it does not specify salary band widths, how vacancies without salaries are handled, or the recency of 'current' data, leaving some behavioral assumptions unstated.

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 and well-structured. It opens with the purpose, then describes the return structure, followed by a clear per-parameter list. Every sentence contributes useful information, with no 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?

For a tool with four parameters and no output schema, the description covers the core behavior, return format, and parameter semantics thoroughly, including cross-references for valid values. It falls short only in not describing salary band boundaries or edge-case behavior (e.g., empty results), but these are minor within the tool's simplicity.

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 fully compensates. It explains each of the four parameters: country with ISO examples, what with AND semantics, category as a reference to list_categories, and location as a hierarchical list with an example and pointer to regional_data. This exceeds what the 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 the current distribution of salaries for a job search as a histogram.' The verb 'get' and resource 'salary distribution' are specific, and the qualifier 'current' distinguishes it from the sibling 'historical_salary'.

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 when a current salary histogram is needed, and parameter semantics provide context. However, it does not explicitly contrast with alternatives like historical_salary or search_jobs, nor does it state when not to use this tool. The only cross-reference is 'See regional_data' for location discovery, which is about parameter values, not 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, the description carries the full transparency burden. It discloses key behaviors: the AND vs OR matching semantics, silent zero-result failures for bad what and where values, and the default distance of 5km. It does not mention return format, pagination behavior, or rate limits, which would be useful but not strictly required for a read-only search.

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 as a list of parameters, each earning its place with specific, actionable information. It is front-loaded with the purpose statement, and every line adds value without unnecessary fluff. The length is justified by the large parameter count.

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

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

The description covers most parameters and provides important caveats, but it omits the return value structure, and a few parameters (page, company, max_days_old) are not described. Given the absence of an output schema, explaining what the tool returns would improve completeness. Overall, it is a strong description for a complex search 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 description must compensate. It explains nearly all 24 parameters, including nuanced distinctions among what, what_or, what_and, what_phrase, what_exclude, and title_only, and documents important behavioral caveats like silent failures and defaults. Only a few parameters (page, company, max_days_old) are left unexplained, which is a minor gap given the breadth covered.

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 opens with 'Search Adzuna's job listings,' which clearly identifies the action (search) and resource (Adzuna's job listings). It does not explicitly compare itself to sibling tools like salary_histogram or top_companies, so it lacks explicit differentiation for purpose.

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 offers internal parameter guidance, e.g., advising to use what_or instead of what for multi-word roles to avoid silent zero results, and references regional_data and list_categories for discovering valid values. However, it does not provide guidance on when to use search_jobs versus other sibling tools such as salary_histogram or top_companies.

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, the description carries the full burden. It discloses the key behavioral trait of returning only the top 5 employers and explains filter semantics (e.g., AND matching for keywords). It also provides helpful cross-references for parameter discovery. Some details like output structure or edge-case handling are omitted, but the description is adequate for a read-only aggregation 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 concise and well-structured: a one-sentence purpose, followed by a compact bullet list of parameters. Every sentence provides useful information, with no redundancy or 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 tool's simplicity (4 params, 1 required, no output schema), the description covers all necessary input semantics and examples. It could be slightly more explicit about return format (e.g., a list of company names with vacancy counts), but the title and first sentence already convey the core output. Overall, it is sufficiently complete for an agent to use the tool correctly.

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 has 0% description coverage, but the tool description fully compensates by explaining every parameter with concrete examples: country codes ('gb', 'us', 'de'), keyword AND semantics, category source, and hierarchical location arrays. This adds significant meaning beyond the raw schema.

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

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

The description clearly states the tool's function: 'Get a leaderboard of the top 5 employers by number of vacancies.' This is a specific verb+resource combination that distinguishes it from siblings like search_jobs or salary_histogram.

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

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

The description gives clear context for when to use the tool, specifying required (country) and optional filters (what, category, location) with examples. It also references related tools (list_categories, regional_data) for discovering valid values. However, it lacks explicit exclusions or alternatives, so it does not fully meet the 'when not to use' criterion.

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