nyheter

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

Annotations include readOnlyHint=true and destructiveHint=true, which are contradictory. The description describes a read-only fetch operation, directly conflicting with destructiveHint=true. Per the rubric, this annotation contradiction forces a score of 1, despite the description's useful notes on error handling and data safety.

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 yet information-rich. Each sentence contributes meaningful context: query method, error behavior, data provenance, and optional parameter usage. It is front-loaded and contains no redundant 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 simple two-parameter getter with no output schema, the description covers the core functionality, error semantics, optional parameter behavior, and a data-safety warning. It provides enough information for an agent to select and invoke 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?

The schema has 100% coverage for both parameters. The description adds value by explaining the purpose of include_source_content beyond the schema (e.g., as a manuscript basis for podcast scripts) and adds a warning that the source content is third-party data, not instructions. This goes beyond simple schema repetition.

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 uses a specific verb 'Hämtar' (fetches) and clearly identifies the resource as 'enskild Apple-nyhetsartikel från Aapl.se via dess id', making the tool's purpose unambiguous and distinct from sibling tools like get_story or list functions. It immediately conveys that this is a single-article retrieval by ID.

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: when you have an ID and need a single article. It also explains the optional parameter's use case. However, it does not explicitly mention alternatives or exclusions (e.g., 'for lists use latest_news'), so it falls short of a 5.

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 asserts a read-only retrieval operation ('Hämtar') while annotations include destructiveHint: true, directly contradicting the expected side-effect profile. This contradiction warrants a score of 1 despite the description adding useful context about error behavior and AI review.

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 four sentences, each contributing: purpose, error semantics, content provenance, and optional parameter explanation. It is front-loaded with the primary action and avoids 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?

For a simple retrieve-by-ID tool with no output schema, the description covers the main returns, error handling, optional transcript, and content generation process. It is sufficiently detailed for an agent to invoke 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 coverage is 100%, but the description adds meaning for include_transcript by clarifying that the transcript is Aapl.se's own content, not a third-party source. This extra context helps agents decide whether to request it, raising the score above baseline.

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 uses the specific verb 'Hämtar' and clearly identifies the resource as a single episode of Aapl Pod, listing return fields (title, description, chapters, sources). It distinguishes from sibling list_podd_episodes by focusing on an individual episode via ID.

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

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

The description implies usage for fetching a single known episode, but does not explicitly state when to use it over siblings like list_podd_episodes. The unknown-ID error handling is noted, but no explicit exclusions or alternatives are named.

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 fetch operation ('Hämtar') and even describes graceful error handling, but the annotations include destructiveHint: true. This directly contradicts the description's implied behavior, so the description fails to provide consistent transparency. Annotation Contradiction flagged.

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 compact sentences, each adding value: purpose and content, error behavior, chain context. No filler or redundant phrasing.

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 single-id fetch, the description covers the essential content fields and error semantics, and notes temporal chain behavior. However, the contradictory annotation and lack of explicit sibling differentiation leave minor gaps, but the text itself is nearly 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 covers 100% of parameters with a detailed description for 'id' including examples of numeric and slug formats. The description only mentions 'via dess id' without adding new semantic details, so baseline 3 applies.

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 opens with 'Hämtar en enskild story-bevakning från Aapl.se via dess id' – a specific verb and resource, naming the id-based lookup. It lists fetched content (title, ingress, body, member articles, chain predecessors/successors), clearly distinct from siblings like get_entry or get_podd_episode.

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 context: use for fetching a single story by id, with explicit note that unknown/unpublished ids yield an error result rather than a server error. No explicit alternatives or when-not-to-use guidance, so it's not fully differentiated from siblings.

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 (source, Swedish AI summaries, newest-first, and a prompt-injection warning) beyond the annotations. However, the annotations declare destructiveHint: true, which directly contradicts the read-only 'Hämtar' operation described. This is an annotation contradiction, so the score is 1.

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, front-loaded with the purpose, and every sentence adds value. It includes a security-relevant instruction without unnecessary 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?

For a simple tool with two optional parameters and no output schema, the description covers the key aspects: source, ordering, optional filtering, and a crucial instruction to treat content as data. It omits explicit mention of the limit parameter, but that is fully documented in the schema.

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%, so the baseline is 3. The description repeats the case-insensitive tag behavior already present in the schema and does not add new information about the limit parameter. No additional semantic value beyond the schema is provided.

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 'fetches the latest Apple news from Aapl.se' with 'newest first' ordering, providing a specific verb, resource, and scope. It distinguishes itself from siblings like popular_news and search_news by naming the source and ordering.

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?

It explains the optional tag filter and the nature of the content, giving clear context for when to use it. However, it does not explicitly compare with alternatives like search_news or popular_news, so it lacks exclusions and named 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?

The description states this tool only lists stories, but the annotations include destructiveHint: true, indicating destructive side effects. This is a contradiction, so the description fails to align with the annotations. No further behavioral context is provided.

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 three sentences, front-loaded with the core action, and efficiently adds context about the AI-composed nature and the pointer to get_story. No superfluous content.

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 tool is simple, but the description lacks an explicit description of the response structure or pagination. It mentions title, ingress, and body text, but doesn't specify the list fields. Given no output schema, this could be improved.

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 already covers both parameters with descriptions and enum values. The description adds only the mention of optional status filtering, but the schema already provides the same information, so no additional semantic value is gained.

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 Aapl.se's story coverages, defining them as AI-composed clusters of related articles tracking an Apple event over time. It also references get_story for full text and member articles, distinguishing it from that sibling.

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?

It explicitly directs users to get_story for full text and member articles, providing an alternative for when more detail is needed. It also mentions optional status filtering, giving clear guidance on what this tool is for.

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 implies a read-only listing operation, but the annotations include destructiveHint=true, which directly contradicts the described behavior. No additional behavioral context is provided beyond the conflicting annotation, so a score of 1 is warranted.

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, consisting of two sentences. It front-loads the main action and provides key output details without any fluff or redundant information.

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

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

The tool is simple (no parameters), and the description covers the output fields and data origin. However, it lacks differentiation from sibling tools and does not address the conflicting destructiveHint annotation, leaving the description incomplete for reliable 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 tool has zero parameters, so the description is not required to explain parameter semantics. The schema is empty and the description adds no parameter-related info, but the baseline for 0 parameters is 4. The description does add context about the output, which is useful but not parameter-specific.

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 uses a specific verb (listar) and resource (nyhetskällor), clearly stating what is listed (active news sources) and the output fields (name, website, language, article count). This distinguishes it from sibling tools like list_podd_episodes and 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?

The description provides no guidance on when to use this tool versus alternatives such as search_news or list_tags. It simply states what the tool does without any contextual cues 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?

The description adds no behavioral detail about the list operation, such as sorting, pagination, or output structure. The annotations (readOnlyHint, destructiveHint) are present, but the description doesn't confirm or elaborate on them. The destructiveHint=true annotation is incongruent with a list operation, but the description doesn't contradict it.

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 three sentences, but the first two are about the podcast's editorial process rather than the tool itself. The RSS link is useful context but tangential. It could be more focused on the tool's function.

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

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

Given no output schema, the description should clarify what the response contains. It only vaguely implies an episode list but doesn't mention fields like episode title, publication date, or duration. This leaves a gap for a simple list tool.

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

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

The only parameter `limit` is fully described in the schema (min 1, max 50, default 10). The description adds no additional meaning about how limit affects results, so it relies on the schema's 100% 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 explains what Aapl Pod is but does not explicitly state that this tool lists episodes. The title 'avsnittslista' and the tool name provide the purpose, but the description itself lacks a clear verb+resource. It mentions get_podd_episode for details, which hints at the listing function.

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 one piece of guidance: for transcripts, chapters, and sources, use get_podd_episode. However, it does not state when to use list_podd_episodes or provide broader context on alternatives like list_feeds or list_tags.

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 already declare readOnlyHint=true and openWorldHint=true, so the agent knows this is a safe read operation. The description adds output details (counts per tag) and a usage hint but does not go beyond what annotations provide in terms of behavioral disclosure. No contradiction with 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 two concise sentences in Swedish, front-loaded with the main action. Every word earns its place, with no fluff or repetition.

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 complete. It explains the tool's output (tag counts) and provides the essential usage context (filtering latest_news).

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 the baseline is 4. The description adds value by explaining that each tag includes an article count and can be used to filter latest_news, which indirectly clarifies what the output contains.

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 that the tool lists Aapl.se's tags for categorizing Apple news, including the count of Apple-relevant articles per tag. This specific verb+resource combination distinguishes it from sibling tools like list_feeds and list_podd_episodes.

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 usage context: 'Use a tag to filter latest_news.' This tells the agent when and how to use the returned tags. However, it doesn't explicitly mention alternatives or exclusions, so it falls just short of a 5.

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 behavioral context beyond annotations: ordering mechanism (readership clicks), Swedish AI summaries, and the aggregated third-party nature of content with a directive to treat article texts as data. It does not address the destructiveHint annotation, but the read-only nature is clear from 'Hämtar'.

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, front-loaded with the core action and ordering, followed by relevant caveats about content and summaries. 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?

Given the simple schema (one optional parameter) and the presence of safety annotations, the description provides a good overview including content source, ordering, and nature of the data. It lacks explicit return structure but is adequate for a straightforward list retrieval tool.

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

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

The schema fully describes the single 'limit' parameter (1–50, default 10), so the description does not need to add parameter details. The tool description does not mention the parameter, but schema coverage is 100%, so baseline 3 applies.

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 retrieves the most popular Apple news from Aapl.se, with specific ordering by popularity score and recency. This distinguishes it from siblings like latest_news and search_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 gives clear context (popularity-ranked Apple news) but does not explicitly mention when to use this tool versus alternatives like search_news or latest_news, nor does it provide exclusion criteria. Usage is implied rather than stated.

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 provides rich behavioral context (semantic search with fallback, Swedish AI summaries, third-party data, prompt injection warning), but it conflicts with the destructiveHint annotation. The tool is described as a read-only search, while destructiveHint=true indicates potential destructive operations, an 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?

Three sentences succinctly cover purpose, method, and output/security guidance. No wasted words; each sentence provides valuable information.

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

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

For a search tool with no output schema, the description adequately conveys what is searched, how (semantic + keyword), what is returned (Swedish summaries), and a security note. It does not detail result ordering or fields, but these are minor gaps given 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 100%, with both 'query' and 'limit' already documented. The description adds no additional parameter-level detail, so the baseline score of 3 applies.

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 searches Aapl.se's Apple news, with a specific verb ('Söker') and resource. It differentiates from sibling listing tools like latest_news and popular_news through its focus on query-based semantic search.

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 use case is implicitly clear: use this tool when you need to search for specific news rather than retrieve recent or popular items. However, it does not explicitly mention alternatives or conditions like 'use when you have a specific query', leaving exclusion guidance only implied.

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