Server Quality Checklist

Tool Scores

• list_sourcesA
  3.5/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It discloses authentication requirements and a specific limitation (handles not exposed). However, it does not mention read-only behavior, pagination behavior, rate limits, or error conditions. The tool is simple, so the transparency is adequate but not comprehensive.

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

  Conciseness5/5

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

  The description is two sentences with no redundancy. The first sentence conveys purpose and output fields; the second provides usage constraints and an alternative. Every sentence adds value, and it is front-loaded with the primary action.

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

  Completeness3/5

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

  Given the simplicity of the tool (1 parameter, no output schema), the description covers the purpose, output fields, and a key usage constraint. However, it fails to explain the limit parameter and does not describe the return format or pagination, which are necessary for correct invocation.

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

  Parameters2/5

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

  Schema coverage is 0%, and the description does not mention the single parameter 'limit'. The purpose and behavior of 'limit' (likely pagination) are not explained anywhere. The description should have clarified this parameter's meaning and default behavior.

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

  Purpose4/5

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

  The description clearly states the tool lists source catalog metadata and enumerates specific fields (type, language, country, audience, political lean). It also distinguishes from sibling coverage_stats by directing users to that tool for aggregate counts, but does not explicitly differentiate from get_breaking, get_feed, or search_news.

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

  Usage Guidelines4/5

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

  The description explicitly states the prerequisite (Standard-tier key or higher) and limitation (handles not exposed). It provides an alternative for a specific use case: 'Use coverage_stats() for public aggregate counts instead.' However, it lacks guidance on when to prefer this tool over other siblings like get_feed.

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

• search_newsA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden for behavioral disclosure. It mentions 'search across the news archive' but does not disclose important behaviors such as whether the operation is read-only (assumed but not stated), pagination, rate limits, authorization requirements, or the meaning of 'urgency score'. The description is incomplete for safe agent decision-making.

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

  Conciseness4/5

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

  The description is concise: one opening sentence followed by a parameter list. It is front-loaded with the main purpose. No wasteful words. However, the parameter list could be slightly more compact (e.g., removing redundant 'Args:' label) but overall well-structured.

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

  Completeness3/5

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

  The description provides adequate input parameter semantics but lacks output schema and return value information. With 5 parameters and no output schema, the agent is left uncertain about response format, error handling, or pagination. The 'tier-limited' hint for days is vague. Given the complexity, the description partially satisfies completeness but has notable gaps.

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

  Parameters5/5

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

  Schema description coverage is 0%, forcing the description to explain all parameters. The description adds meaningful context: 'query: search terms (matched against title + content)', 'min_score: minimum urgency score (0-10)', 'language: 'ru', 'en', etc. Empty = all', 'days: history window (tier-limited)', 'limit: max results (capped at 50)'. This fully compensates for the schema's lack of descriptions and adds value beyond raw names and types.

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

  Purpose5/5

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

  The description clearly states 'Full-text keyword search across the news archive', specifying a specific verb ('search') and resource ('news archive'). This distinctly differentiates from siblings like coverage_stats, get_breaking, get_feed, and list_sources, which serve different purposes (stats, breaking news, feed, sources).

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

  Usage Guidelines3/5

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

  The description does not provide explicit guidance on when to use this tool versus alternatives. It implies usage for full-text search, but lacks any 'when to use' or 'when not to use' context. The sibling tools hint at different functionality, but the description itself offers no comparative or conditional advice.

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

• coverage_statsA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden. It discloses that the tool is open-access ('No API key required') and implies real-time data ('Live'), but does not detail other behavioral traits like rate limits, data freshness, or whether it is read-only. The transparency is adequate but not thorough.

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

  Conciseness5/5

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

  The description is exceptionally concise: one sentence listing key statistics and an access note. It is front-loaded with the purpose and wastes no words.

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

  Completeness4/5

  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 nearly complete. It specifies the types of data returned. However, it could mention if results are paginated or if there is a limit, but for a stats endpoint this is acceptable.

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

  Parameters3/5

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

  The tool has zero parameters and schema description coverage is 100%, so the baseline is 3. The description does not need to add parameter semantics. It appropriately focuses on the output.

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

  Purpose5/5

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

  The description clearly states the tool returns 'Live coverage stats' and enumerates specific statistics (total articles, breaking count, today's volume, active sources, countries, language counts). This distinguishes it from sibling tools like get_breaking (breaking news), get_feed (feed), list_sources (sources), and search_news (search). The verb is implicit but clear.

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

  Usage Guidelines3/5

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

  The description mentions 'No API key required,' which implies ease of use, but lacks explicit guidance on when to use this tool versus alternatives. It does not state when not to use it or provide context for decision-making. The guidance is minimal.

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

• get_feedA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses that articles are pre-scored, classified by political lean, topic, country, audience, and de-duplicated. This adds context beyond the schema, though it does not mention return format or pagination.

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

  Conciseness4/5

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

  The description is moderately long but well-structured with a brief intro followed by a parameter list. Each line adds value without unnecessary fluff. It could be slightly more concise, but it is effective.

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

  Completeness4/5

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

  All 8 parameters are thoroughly documented. Despite lacking an output schema, the description explains the article enrichment (scoring, classification). It is complete for the tool's purpose, though it omits specifics on response structure like pagination.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the description provides detailed explanations and allowed values for all 8 parameters. For example, it lists all topics, political leans, audience types, and gives usage hints like 'min_score: Use 7+ for breaking-only'. This greatly aids an AI agent in selecting correct parameter values.

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

  Purpose5/5

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

  The description clearly states the tool retrieves a filtered feed of enriched news articles, with specific verb 'Get' and resource 'feed'. It distinguishes from siblings like 'get_breaking' and 'search_news' by emphasizing pre-scored, classified, and de-duplicated articles.

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

  Usage Guidelines3/5

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

  The description provides implied usage context (e.g., 'Use 7+ for breaking-only') but does not explicitly state when to use this tool versus alternatives like 'get_breaking' or 'search_news'. No direct guidance on 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.

• get_breakingA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description covers behavioral traits well: it states defaults (min_score=7, limit default 20 but capped at 50), handling of empty values for country and topic, and the brevity of results. It does not mention read-only nature, but that is implied by 'get'. The cap on limit is an important behavioral detail.

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

  Conciseness5/5

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

  The description is very concise, with 5 short lines front-loading the purpose and then listing parameters. Every sentence adds value; there is no redundancy. It efficiently conveys essential information.

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

  Completeness4/5

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

  For a simple filtered-list tool with no output schema, the description is mostly complete: it covers all parameters, defaults, and a sibling reference. It could optionally describe the return format (articles), but that is inferable. The lack of output schema is not a gap here.

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

  Parameters5/5

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

  The input schema has 0% description coverage, so the description fully compensates by explaining each parameter: country (ISO-2, empty=all), topic (see get_feed, empty=all), min_score (default 7), and limit (max 50). It adds constraints and defaults beyond the schema's bare types.

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

  Purpose5/5

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

  The description clearly states 'Get recent breaking news (high urgency)' with a specific verb and resource, and it distinguishes from siblings by emphasizing urgency and a default min_score, which is unique to this tool. The reference to get_feed for topic filtering also helps differentiate.

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

  Usage Guidelines3/5

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

  The description implies usage for urgent/breaking news by setting a default min_score of 7, but it does not explicitly state when not to use it or directly compare to alternatives like get_feed or search_news. The guidance is implied but not fully explicit.

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