Server Quality Checklist

Tool Scores

• listing_delistingD
  1.4/5.0
  Behavior1/5

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

  No annotations are provided, and the description gives no behavioral details such as whether the tool is read-only, what it returns, or any side effects. The description 'listing-delisting' offers no transparency.

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

  Conciseness2/5

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

  The description is extremely brief, but this is under-specification rather than effective conciseness. It does not front-load useful information and fails to earn its place as a meaningful description.

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

  Completeness1/5

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

  With no output schema, no annotations, and a one-word description, the tool lacks essential context. There is no indication of what the tool returns, how it behaves, or how it relates to the other crypto tools.

  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 input schema fully describes the 'sort_by' parameter with its meaning ('Sort by published or event date'), so schema coverage is 100%. The tool description adds no extra semantic value, but the schema carries the burden adequately.

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

  Purpose1/5

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

  The description 'listing-delisting' is a tautology that simply restates the tool name without indicating any specific action or resource. It fails to distinguish itself from sibling tools or explain what it actually does.

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

  Usage Guidelines1/5

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

  There is no guidance about when to use this tool versus the sibling tools (e.g., coins_price_list, crypto_rates). No context, prerequisites, or alternatives are mentioned.

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

• crypto_txsD
  1.6/5.0
  Behavior1/5

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

  No annotations are present and the description is just the tool name. The description discloses nothing about side effects, safety, rate limits, or any behavioral traits, placing the full burden on the description which it fails entirely.

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

  Conciseness2/5

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

  While the description is extremely short (one word), this is under-specification rather than conciseness. It lacks any structuring or content that would help an agent understand the tool, similar to the 'Process' example in the calibration.

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

  Completeness1/5

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

  For a tool named 'crypto_txs' with no description, no annotations, no output schema, and no parameters, the information is entirely inadequate. An agent has no clue what transactions are involved, what inputs/outputs to expect, or how to invoke it correctly.

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

  Parameters4/5

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

  The schema has zero parameters, and the schema coverage is 100% (vacuously). With no parameters to describe, the baseline of 4 applies; the description need not explain parameters, though it also adds no additional parameter-related meaning.

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

  Purpose1/5

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

  Tautological: description restates name/title.

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

  Usage Guidelines1/5

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

  There is no guidance on when to use this tool versus alternatives. No context, prerequisites, or exclusions are provided, leaving the agent to guess its purpose.

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

• coins_price_listC
  2.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It only says 'returns prices' and does not mention pagination, required base_currency, or any other behavioral traits like result format or limits. This is minimal disclosure.

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

  Conciseness2/5

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

  The description is a single sentence, which is concise, but it is under-specified and does not convey useful information. It reads as a statement about a project rather than a tool description, so it does not earn its place.

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

  Completeness2/5

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

  Given the lack of annotations and output schema, the description should provide more context about the returned data and parameters. It only states the obvious (prices) and does not explain the pagination or base_currency behavior, leaving significant gaps.

  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?

  Schema description coverage is 100%, so each parameter has a description. The tool description adds no extra semantics beyond the schema, so the baseline of 3 is appropriate.

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

  Purpose3/5

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

  The description states the tool returns cryptocurrency prices, which indicates the core function, but uses the vague phrasing 'The project' and does not specify that it's a paginated list or how it differs from sibling tools like crypto_rates. It is a clear enough action but lacks specificity.

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

  Usage Guidelines2/5

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

  No guidance is provided about when to use this tool versus alternatives such as crypto_rates. There is no mention of context, prerequisites, or 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.

• crypto_historical_articlesC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavior. It mentions sorting and a 30-day window, but omits that the time_frame parameter can override that window, and doesn't mention pagination behavior, response format options, or source filtering. This is a significant gap for a read tool with no schema-level behavioral hints.

  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 short sentences, front-loaded with the core action and result. There is no filler; every word earns its place. The structure is highly concise and easily scannable.

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

  Completeness2/5

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

  With 5 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain the time_frame override, pagination defaults, format selection, or source filtering, and gives no indication of what an Article contains. The agent would need to infer too much from the schema and sibling tools.

  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?

  Schema coverage is 100%, so the baseline is 3. The description adds minimal value beyond the schema, mainly the 'last 30 days' context which relates to time_frame. However, it may unintentionally mislead by implying a fixed window rather than a configurable one, so it doesn't enhance parameter understanding.

  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 identifies the action ('Returns a list of Articles'), the resource (Articles), and scopes it to the last 30 days with newest-first sorting. It does not explicitly differentiate from sibling tools like crypto_articles or latest_news, but the time-frame and sorting details provide some distinction.

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

  Usage Guidelines2/5

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

  There is no guidance on when to use this tool versus alternatives. It simply states what it does, with no mention of exclusions, prerequisites, or contextual recommendations. The agent is left without direction for tool selection.

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

• crypto_ratesC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It only states that prices are returned, which implies a read operation, but it does not describe output format, rate limits, error behavior, or limitations relative to sibling tools. The description adds little beyond the basic purpose.

  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 a single concise sentence that front-loads the primary purpose. It contains no filler or redundant phrasing, making it easy to parse quickly.

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

  Completeness2/5

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

  The tool has 2 parameters, no output schema, and no annotations, yet the description only covers the basic purpose. Missing details include the meaning of 'detailed', usage context vs. siblings, and expected return shape. The description is too sparse to fully guide an agent in selecting and invoking the tool correctly.

  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?

  Schema description coverage is 100% (both params have description fields), so baseline is 3. The description adds context that 'currency' is the base currency, but the 'detailed' parameter has an empty description and is not explained anywhere. The description does not significantly enhance parameter understanding beyond the schema.

  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 states a clear action ('Returns cryptocurrency prices') and the resource ('cryptocurrency prices') based on a base currency. It does not explicitly differentiate from sibling tools like coins_price_list, but the wording is specific enough to understand the core function.

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

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives (e.g., coins_price_list, fiat_supported). There is no mention of preferred scenarios, prerequisites, or exclusions, leaving the agent to guess based on the minimal description.

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

• crypto_articles_search_by_keywordsB
  3/5.0
  Behavior2/5

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

  With no annotations, the description must carry the full behavioral disclosure. It mentions sorting (newest to oldest) and a fixed 24-hour window, but fails to mention pagination, response formats, or the configurable timeframe. The 'last 24 hours' statement is also inconsistent with the time_frame parameter, reducing transparency.

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

  Conciseness3/5

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

  The description is only two sentences but contains redundancy: 'can be filtered using keywords' and 'Specify keywords in the query parameters to refine the search' overlap. It is concise but not free of waste and includes an inaccurate fixed-time statement.

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

  Completeness2/5

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

  The description is insufficient for a 5-parameter tool with no output schema and no annotations. It omits pagination behavior, format options, and timeframe flexibility. The parameter descriptions in the schema compensate partially, but the narrative leaves gaps for an agent to correctly set expectations.

  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?

  Schema description coverage is 100%, so the baseline is 3. The description adds minimal value beyond reiterating keyword filtering; it does not elaborate on page, limit, format, or time_frame. The schema already provides adequate parameter explanations.

  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 retrieves crypto-related articles and filters by keywords, but it does not distinguish this tool from siblings like latest_news_search_by_keyword or crypto_articles. It specifies a time scope of 'last 24 hours' which may be misleading given the time_frame parameter supports other ranges.

  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 by stating 'Specify keywords in the query parameters to refine the search,' giving basic how-to guidance. However, it does not explain when to use this tool versus alternative search tools, nor does it mention the adjustable time_frame.

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

• sentiment_analysisB
  3.1/5.0
  Behavior2/5

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

  No annotations are present, so the description bears full responsibility for behavioral disclosure. It only restates the core action without revealing behaviors like what happens when no interval is provided, which sentiment labels are counted, or the structure of the returned data. It does not contradict any annotations since there are none, but it adds minimal behavioral context.

  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 a single, direct sentence containing no filler or redundant information. Every word earns its place, making it easily scannable and efficient.

  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 tool's low complexity and complete parameter documentation, the description is minimally viable. However, it leaves open questions about the optional interval's default and the exact return format, which are not covered by an output schema. For an agent to invoke it confidently, a bit more context about these behaviors would be needed.

  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 input schema provides complete coverage of the lone parameter 'interval' with format examples, so the schema largely carries parameter meaning. The description's phrase 'selected time interval' mirrors the schema without adding extra semantic depth, thus the baseline of 3 applies.

  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 it returns the number of articles grouped by sentiment label for a time interval. It uses a specific verb ('returns') and identifies the resource (articles by sentiment label), which distinguishes it from generic list tools. However, it does not explicitly mention any sibling tool like article_statistics, so it misses the highest level of differentiation.

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

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives. The 'selected time interval' hints at the interval parameter, but the description does not explain whether the parameter is required, optional, or what the default behavior is, nor does it suggest any exclusions or alternative tools.

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

• crypto_articlesB
  3.2/5.0
  Behavior3/5

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

  The description discloses the time window (last 24 hours) and sorting order (newest to oldest), which are helpful behavioral traits. However, it does not mention pagination, response format, or any caveats, and with no annotations the burden on the description is higher.

  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 at two sentences, with the main purpose front-loaded. Every sentence provides relevant information without unnecessary detail.

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

  Completeness2/5

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

  There is no output schema, so the description should explain the structure of the returned articles. It only says 'list of Articles' without specifying fields or count. It also lacks pagination behavior and differentiation from similar tools, making it incomplete for a new agent.

  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?

  Schema description coverage is 100%, so every parameter has a description. The tool description adds no additional parameter semantics, which is acceptable given the schema already documents the parameters.

  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 returns a list of Articles from the last 24 hours, sorted newest to oldest. It specifies the verb and resource, but does not differentiate it from sibling tools like 'latest_news' or 'crypto_articles_search_by_keywords'.

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

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives. It does not mention any exclusions or the existence of search-related siblings, leaving the agent uncertain about selection.

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

• latest_news_search_by_keywordB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits. It only states the core search function without mentioning whether it is a read-only operation, any pagination behavior, return format, or potential limitations. The word 'search' implies a read operation, but this is not explicit, and there is no disclosure of side effects or constraints.

  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 a single, concise sentence that gets straight to the point: 'Search for articles that contain a specific keyword in the title.' No filler, no repetition. It is appropriately sized and front-loaded.

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

  Completeness2/5

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

  For a simple search tool, the description covers the basic purpose, but it lacks essential context given the absence of annotations and output schema. There is no mention of what the tool returns (e.g., article list, metadata), no usage guidance, and no differentiation from sibling tools. Given the complexity of the parameter set and sibling ambiguity, this is incomplete.

  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?

  Schema description coverage is 100%, so the baseline is 3. The description adds the semantic clarification that the keyword is matched in the title, which is useful. However, the schema descriptions are only example values (e.g., 'Example value: Microsoft'), providing no real explanation of what 'page' and 'page_size' do. The description does not compensate for this gap.

  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 action ('Search for articles'), the resource ('articles'), and the precise scope ('contain a specific keyword in the title'). This distinguishes it from sibling tools like crypto_articles_search_by_keywords, which likely search across full text, and latest_news, which may not have a keyword search. The verb and resource are 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.

  Usage Guidelines2/5

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

  The description gives no guidance on when to use this tool versus alternatives. It does not mention that it is title-specific or suggest other tools for keyword searching in full content. Without exclusions or alternative recommendations, the agent lacks sufficient context to choose this tool over similar siblings.

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

• article_statisticsA
  3.5/5.0
  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. It only states what is returned and the time intervals, but does not disclose details such as which RSS feeds are included, whether statistics are aggregated or per-feed, or any limitations. This is minimal behavioral disclosure.

  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 a single, focused sentence that front-loads the key function ('Returns statistics') and then specifies the time intervals. It is concise with no wasted words.

  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?

  While the tool is simple (no parameters, no output schema), the description is somewhat vague about 'various RSS feeds' and does not clarify what the statistics look like (e.g., counts per feed, totals, or a breakdown). It provides enough for basic comprehension but leaves gaps for an AI agent to know exactly what to expect.

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

  Parameters4/5

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

  The tool has zero parameters, and the schema is empty, so the baseline is 4. The description adds no parameter information, which is acceptable given none exist.

  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's function: returns statistics on article counts over specific time intervals (1, 4, 8, 12, 24 hours) from RSS feeds. This uses a specific verb and resource, and distinguishes it from sibling tools that return article content or lists.

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

  Usage Guidelines2/5

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

  The description implies usage for aggregate counts over time but does not explicitly state when to use this tool versus alternatives like latest_news or crypto_articles. No exclusions or alternative tool names are mentioned.

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

• latest_newsA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It does disclose the sort order (published_utc) and pagination support, but it omits other behaviors such as authentication requirements, rate limits, or the shape of the returned articles. It is a simple read operation, so the gaps are not severe, but richer context would help.

  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 a single concise sentence that is front-loaded with the core action and includes key details (sort and pagination). Every word earns its place, with no fluff or unnecessary repetition.

  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 list-retrieval tool with two optional parameters and no output schema, the description adequately covers the main functional behavior. It states the resource, sort order, and pagination support. However, it does not mention the structure of returned articles or any source context, which could be inferred from the tool name and siblings. Overall, it is sufficient but not exhaustive.

  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?

  Schema description coverage is 100% (both properties have descriptions), but those descriptions are only example values ('Example value: 1') and add little semantic meaning. The tool description mentions 'pagination support' which implies page and page_size roles, and the parameter names are self-explanatory. With baseline 3 for high coverage, no credit beyond that is warranted.

  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's purpose: 'Retrieve a list of articles sorted by published_utc with pagination support.' It uses a specific verb (retrieve) and resource (articles), and the sorting and pagination details distinguish it from sibling search tools like latest_news_search_by_keyword.

  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 explicitly state when to use this tool versus alternatives, but the name plus the existence of search siblings imply this is for general latest-news retrieval while search tools are for keyword-based queries. No exclusions or alternatives are explicitly named, so guidance is only implied.

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

• source_listA
  4.2/5.0
  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 clearly states the read-only nature implicitly and provides usage context, but does not disclose behaviors like pagination, sorting, or authentication. For a simple list operation, 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.

  Conciseness5/5

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

  Two sentences, front-loaded with the primary purpose, and includes a practical example. No wasted 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 simplicity (no params, no output schema), the description provides sufficient context by linking to the endpoint and example usage. It does not describe the exact return format, but the example implies string identifiers, which is acceptable.

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

  Parameters4/5

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

  The tool has zero parameters, so the description need not explain parameter semantics. The description adds context about the 'source' parameter used in the endpoint, which is helpful.

  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 explicitly states the tool returns a list of sources for the '/crypto/articles' endpoint, with a concrete example. This clearly distinguishes it from sibling tools like latest_news or crypto_rates.

  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?

  It clearly indicates when to use this tool (to obtain valid source values for filtering articles) and provides context via the example. However, it does not mention exclusions or alternative tools, so it lacks explicit when-not-to-use guidance.

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

• fiat_supportedA
  4.3/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It states 'Returns', implying a read-only operation, but it does not disclose other behavioral traits such as response format, data freshness, or any access requirements. For a simple list tool, this is adequate, but more detail could enhance transparency.

  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 a single sentence with no filler, front-loading the essential purpose and output. Every word contributes to clarity, making it highly concise and well-structured.

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

  Completeness5/5

  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 fully explains the return value: a list of fiat symbols and names. This is complete for an agent to use the tool correctly without needing additional context.

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

  Parameters4/5

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

  The input schema has zero parameters, so the description correctly does not attempt to explain parameter semantics. The baseline of 4 applies because there are no parameters to describe, and the focus on output is appropriate.

  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?

  Description clearly states a specific action ('Returns') and resource ('list of all supported fiat currency symbols and their full names'). It is distinct from sibling tools, which focus on crypto rates, news, and transactions, making the tool's purpose unambiguous.

  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?

  While the description does not explicitly mention when to use vs alternatives, the context is clear: this is the tool for fiat currency data. There is no sibling tool for fiat, so the absence of explicit exclusions is acceptable. The purpose itself provides sufficient usage context.

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