nyheter

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

The description describes a read-only fetch, but annotations include destructiveHint=true, a contradiction. Thus transparency is severely undermined.

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 main action and includes key details (error handling, content nature, optional parameter use) without unnecessary verbiage.

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 (2 params, no output schema), the description adequately covers purpose, error case, content type, and optional parameter intent, though the annotation contradiction detracts.

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 coverage is 100% with descriptions already adding meaning. The description reinforces the source content usage for script writing but doesn't add significant new semantics 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 fetches a single Apple news article by id (verb+resource). While it doesn't explicitly distinguish from siblings, its purpose is 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?

No explicit guidance on when to use this tool versus alternatives; it only implicitly specifies use for known ids. No when-not or alternative names are provided.

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?

The description states a read-only operation ('Hämtar'), but the annotation destructiveHint: true implies mutation. This is a direct contradiction (Annotation Contradiction). Additionally, while the description adds error handling and AI generation info, the contradiction severely undermines trust.

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?

Description is front-loaded with purpose, followed by error behavior, content creation note, and optional parameter explanation. Each sentence serves a purpose, though slightly verbose. Efficient overall.

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?

Covers what the tool returns, error handling, and optional behavior. Lacks explicit return value details (no output schema) but sufficient for a simple retrieval tool. Annotation contradiction is a separate issue.

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 coverage is 100%, but the description adds extra context for include_transcript (notes it is Aapl.se's own content, not third-party) beyond the schema's description. For episode_id, the description provides an example value, similar to schema. Overall adds marginal value beyond 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 'Hämtar' (retrieves) and the specific resource 'ett enskilt avsnitt av Aapl Pod', listing returned fields (titel, beskrivning, kapitel, källor). It distinguishes from siblings like list_podd_episodes (which lists all episodes) and other get_ 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 context for unknown IDs (returns error, not server error) and mentions optional transcript inclusion. However, lacks explicit when-not-to-use or direct comparisons to alternatives, though implicitly differentiated from list 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?

Description describes a read-only fetch operation, but annotations include destructiveHint: true, which contradicts the behavior described. No clarification is provided, leading to a contradiction.

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?

Two sentences packed with necessary details (fields returned, error behavior, chain info). No redundancy, front-loaded with core action.

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?

Description covers input, output fields, error scenario, and chain behavior. Missing output schema is compensated by listing return contents. Slightly incomplete regarding response format but acceptable.

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?

Only one parameter 'id' with full schema coverage; the description adds no additional meaning beyond the schema's clear explanation of numeric or slug formats.

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?

Description clearly states it fetches a single story by id, listing included fields (title, ingress, full body, member articles, chain info). Distinguishes from siblings like get_entry or latest_stories by specifying the 'story' resource and cluster/chain details.

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?

Implies use for retrieving a specific story by id, and explains error handling for unknown ids. Does not explicitly state when not to use or compare to alternatives, but intention is 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?

Adds context beyond annotations: specifies content is aggregated third-party news and advises treating article texts as data, not instructions. Annotations already mark readOnly and destructive hints; no contradiction.

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?

Three concise sentences, each adding value: main action, optional filter, and critical content warning. No 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?

For a simple list tool with good annotations and schema, description is nearly complete. Lacks explicit return value format, but ordering and source are covered.

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

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

Schema coverage is 100%, but description reinforces parameter meanings: tag is optional filter, limit is number of articles (default 10). Adds slight extra context beyond 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?

States exactly what the tool does: retrieves latest Apple news from a specific source (Aapl.se) with ordering (nyast först). Clearly distinguishes from siblings like search_news and popular_news.

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?

Describes optional filtering by tag, but lacks explicit guidance on when to use this tool over siblings like search_news or popular_news. However, the purpose and sibling names imply 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?

The description states 'Listar' (lists), implying a read-only operation, but the annotations include destructiveHint: true, which contradicts the description's implied behavior. This is flagged as Annotation Contradiction.

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 paragraph of three sentences, front-loaded with the purpose, then explains the nature of the tool, and ends with usage guidance. No redundant words 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?

The description explains the nature of the tool (AI-composed clusters, not third-party), mentions optional filtering, and refers to get_story for details. For a listing tool with two optional parameters and no output schema, it provides sufficient context, though it does not describe the exact output format.

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?

Both parameters have descriptions in the schema (100% coverage). The description adds context: it mentions filtering by status, the limit range, and states a default value of 10 for limit, which is not specified in the schema. This adds value 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 'Listar Aapl.se:s story-bevakningar' with a specific verb and resource, and explains they are AI-composed clusters of related articles following an Apple event. It distinguishes from sibling tools like get_story (which retrieves full text) and latest_news (individual articles).

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 mentions optional filtering by status and explicitly directs to use get_story for full text and member articles, providing clear context for when to use this tool versus an alternative. It does not explicitly state when not to use this tool.

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?

Annotations indicate both readOnlyHint=true and destructiveHint=true, which is contradictory. The description claims only a listing operation with no mention of destructive behavior, failing to resolve the conflict. This creates a serious inconsistency for the 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?

Two concise sentences provide clear, front-loaded information with no unnecessary words. Every sentence adds value.

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 explains what is listed but lacks details on return structure, ordering, or pagination. Given no output schema, a more complete description of the expected output format would be beneficial.

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

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

The tool has no parameters, so the description does not need to add parameter details. The baseline for zero parameters is 4, and the description does not detract from this.

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 it lists active news sources aggregated by Aapl.se, specifying the details included (name, website, language, article count). While it distinguishes the tool's function from siblings, it does not explicitly differentiate from similar listing tools like list_tags.

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 explicit guidance on when to use this tool versus alternatives. The purpose is implicit as a simple list, but the description lacks context for when to choose list_feeds over other listing or search 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?

Annotations include both readOnlyHint=true and destructiveHint=true, a clear contradiction that the description does not resolve. The description provides no details on ordering, pagination, or side effects, leaving behavioral assumptions unaddressed.

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 brief (4 sentences) but misallocates space to describe the podcast rather than the tool's function. It includes an RSS link that is ancillary. Could be more focused and 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?

No output schema exists, yet the description fails to specify what the tool returns (e.g., list of episodes, metadata fields). The only hint is the reference to 'get_podd_episode' for details, but the response format is entirely omitted.

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 fully covers the single 'limit' parameter with description and constraints (1–50, default 10). The tool description adds no further explanation for this parameter, so it meets the baseline for high 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 focuses on describing the podcast ('Aapl Pod är Aapl.se:s egen korta ljudbriefing...') rather than stating the tool's action. The verb 'list' is absent; the purpose is only implied by the tool name. This is a tautology of the title without functional clarity.

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 explicit guidance on when to use this tool versus siblings like 'get_podd_episode' or 'search_news'. The mention that 'Transkript, kapitel och källor hämtas per avsnitt med get_podd_episode' hints at a workflow but does not clarify selection criteria.

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

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

Annotations include readOnlyHint=true, so the description does not need to add behavioral details, but it also does not clarify the contradictory destructiveHint=true annotation. The description is consistent with read-only behavior but does not explain the inconsistency.

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

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

The description is two sentences with no unnecessary words. It is front-loaded with the purpose and includes a usage hint, making it highly concise and effective.

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 (no parameters, no output schema), the description is largely complete. It explains the output (tags with article counts) and a use case. Missing a brief note on the return format, but not critical.

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 no parameters, so the input schema covers 100%. The description does not need to add parameter information; baseline score 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 lists tags used for categorizing Apple news, including article counts, and explains its purpose in filtering latest_news. It distinguishes itself from sibling tools like get_entry and latest_news.

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 using tags to filter latest_news, indicating a clear use case. However, it does not specify when not to use the tool or mention alternatives.

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?

Annotations include readOnlyHint and destructiveHint (somewhat contradictory), but the description adds value by noting that summaries are AI-generated and content is aggregated third-party data. It advises treating article texts as data, which is useful behavioral guidance beyond the 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 short and front-loaded with the main purpose. It uses two sentences to convey source, ordering, summaries, and data handling. Minor multilingual mix but overall efficient.

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 simple tool with one optional parameter and no output schema, the description covers source, ordering, content nature, and AI summaries. It is sufficient for an agent to understand what the tool returns and how to interpret the 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 input schema has 100% description coverage for the limit parameter, detailing range and default. The description does not add any additional semantics beyond what the schema provides, so baseline score of 3 is appropriate.

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

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

The description clearly states the verb ('Hämtar' retrieves), the specific resource (popular Apple news from Aapl.se), and the ordering (by popularity score then newest). It distinguishes from siblings like latest_news and search_news by emphasizing the popularity-based ranking.

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 does not explicitly provide usage guidelines or contrast with alternative tools. It implies use for popular news but lacks direct 'when to use' or 'when not to use' statements, which is a gap given the availability of siblings like latest_news and search_news.

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?

The description adds useful context (semantic search, fallback, AI summaries, warning about content treatment). However, it contradicts the 'destructiveHint: true' annotation; the tool is clearly read-only. This inconsistency harms 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 concise (4 sentences) and front-loaded with the main action. It efficiently conveys key points without 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?

For a search tool without output schema, the description explains the return type (Swedish AI summaries) and mentions fallback behavior. However, it lacks detail on response structure and sorting, and the contradictory annotations reduce 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?

Schema description coverage is 100%, so baseline is 3. The description does not add extra parameter-level details beyond the schema, but that is acceptable given full 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 action (search) and resource (Apple news from Aapl.se). It mentions semantic search and automatic fallback, providing specific details. However, it does not explicitly distinguish from sibling tools like latest_news or popular_news, slightly lowering clarity.

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 describes what the tool does but offers no guidance on when to use it versus alternatives. It implies usage for searching Apple news but does not provide exclusions or context-specific recommendations.

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