Server Quality Checklist

Tool Scores

• github_trendC
  2.9/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It explains the growth_ratio semantics and the comparison window, which is useful, but it does not describe output shape, data limits, or whether the result is a list of repos or an aggregate metric.

  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 a single focused sentence with no filler. The key comparison and metric interpretation are front-loaded, though the meaning of query could have been added without much loss of conciseness.

  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 tool with no annotations, no output schema, and a required query parameter, the description is too thin. It leaves critical unknowns: what format query takes, what the response contains, and how growth_ratio is derived beyond the vague 'vs prior window' phrasing.

  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 description coverage is 0%, so the description must compensate. It indirectly explains window_days via 'last N days' and 'prior window', but the required query parameter is entirely unexplained, leaving the agent to guess what should go in it.

  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 identifies GitHub repos as the resource and defines the core trend metric (growth_ratio comparing recent vs prior window). It is specific enough to distinguish this from a plain repository info tool, though it lacks an explicit verb like 'returns' or 'computes'.

  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 siblings such as github_repo_signal or hn_trend. The context implies it is for trend analysis, but no explicit conditions or alternatives are provided.

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

• hn_trendB
  3.2/5.0
  Behavior3/5

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

  With no annotations, the description carries the transparency burden and does add useful behavioral detail: it compares the last N days against the prior window and defines growth_ratio > 1 as accelerating attention. However, it does not describe query semantics, window_days defaults, edge cases like zero prior counts, or the return shape.

  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 core metric and adding an interpretation of the result. Every word contributes to understanding the tool's function.

  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 tool with no output schema, no annotations, and two parameters, this description is too sparse. It does not define the required query parameter, explain defaults or edge cases, or provide enough information to decide when to use this tool over its siblings, making confident invocation difficult.

  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 description coverage is 0%, so the description must compensate for both parameters. It only hints that window_days maps to 'last N days'; the required query parameter is never mentioned or explained, leaving the agent to guess what string should be supplied.

  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 names a specific resource and metric: Hacker News story count compared across two time windows, with growth_ratio as the output. It is clear about the tool's analytical intent, but it does not explicitly distinguish itself from the sibling hn_signal tool, leaving some differentiation to inference.

  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 phrase 'accelerating attention' implies this tool is for measuring acceleration in Hacker News story interest, but there is no explicit when-to-use or when-not-to-use guidance. It names no alternatives and gives no conditions for preferring hn_trend over hn_signal or github_trend.

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

• npm_downloadsB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral disclosure burden. It clearly indicates this is a download-count lookup, but it does not define whether 'last-month' means the previous calendar month or a trailing 30-day window, nor does it describe the return format, data source, or error behavior.

  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 the core output stated first and the use-case context added parenthetically. It is concise and every word contributes meaning.

  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?

  For a one-parameter tool, the description gives enough to understand the basic input and output, but it omits precise time-window semantics, output shape, and failure cases. Since there is no output schema and no annotations, the description is minimally adequate rather than complete.

  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 0%, so the description must clarify the 'package' parameter. It adds that the parameter refers to an npm package, which is useful, but it does not provide examples or mention format details such as scoped package names.

  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 specific metric ('Last-month downloads') for a specific resource ('npm package'), which clearly conveys what the tool returns. It is distinguishable from pypi_downloads by the npm scope, though it does not explicitly contrast with siblings.

  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 parenthetical '(comparable-product demand)' implies a use case, but there is no explicit guidance on when to choose this tool over pypi_downloads or the GitHub/HN alternatives. No exclusions or alternative routing are provided.

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

• hn_signalA
  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 full behavioral burden. It does disclose the core behavior (returns a story count aggregated over N days), but omits details like query matching semantics, day boundaries, and whether the result is a raw number or an object.

  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?

  One compact sentence with no filler; the core behavior and intent are front-loaded and the parenthetical adds useful context without bloating the text.

  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?

  For a low-complexity tool with no output schema and no annotations, the description gives the essential what and why, but not enough to fully preempt ambiguity about return shape, parameter constraints, or relation to hn_trend. It is minimally viable rather than comprehensive.

  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 0%, so the description must compensate. It maps 'query' to the search term and 'days' to 'last N days', which adds meaning beyond the raw schema. However, it leaves out query syntax, default/range for days, and whether days is inclusive.

  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 operation: count Hacker News stories for a query over a time window, and adds the 'tech-audience attention proxy' framing. It does not explicitly distinguish itself from the sibling hn_trend, but the verb/resource/scope are 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 conveys a use case (query-level HN story count as attention signal) but gives no explicit when-to-use or when-not-to-use guidance. With hn_trend as a sibling, the agent must infer which tool is appropriate rather than being told.

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

• pypi_downloadsA
  3.5/5.0
  Behavior2/5

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

  There are no annotations, so the description alone must disclose behavior. It only reveals the time window ('last-month') and the resource, but gives no details about return format, error handling, edge cases like unknown packages, or whether any side effects exist. The description carries minimal behavioral burden for a tool with no annotation support.

  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 that immediately leads with the primary output metric and resource. There is no filler, and the parenthetical adds useful context without bloating the definition.

  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?

  For a simple read-only tool with one parameter and no output schema, the description covers the essential input semantics and the metric returned. However, it omits details like what the response looks like, how 'downloads' are counted, and behavior for invalid or unknown packages. Given the absence of annotations, this is adequate but not fully complete.

  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 one parameter ('package') with zero description coverage. The description adds meaningful semantics by identifying it as a PyPI package, which tells the agent what value to provide. It doesn't specify format or examples, but for a single-parameter tool this is a significant clarification over the raw schema.

  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 that the tool returns last-month downloads for a PyPI package, which is a specific resource and time window. The phrase 'PyPI package' also distinguishes it from siblings like npm_downloads, GitHub, or Hacker News tools, even without explicitly naming them.

  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 given on when to use this tool versus alternatives. The parenthetical 'comparable-product demand' hints at a possible use case, but it does not explain when to choose pypi_downloads over npm_downloads or other sibling tools, nor does it mention any exclusions or prerequisites.

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

• github_repo_signalA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the behavioral transparency burden. It discloses the operational output (repo count and top-star sums) and the semantic purpose. It does not mention query syntax expectations, limitations, rate limits, or whether results are live or cached, but the read-only nature is reasonably inferable from 'count and sums.'

  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, efficient sentence. It front-loads the concrete output and then adds the interpretive context in a parenthetical. Every word contributes meaning; there is no filler or redundancy.

  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 tool with one simple parameter, a high-level output description, and no output schema, the description is nearly complete. It tells the agent what will happen with the query and what the result represents. It would be more complete with a note on query formatting or a pointer to github_trend for comparison, but overall it covers the essentials.

  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 schema already describes the only parameter as 'GitHub search query' with 100% coverage, which sets the baseline at 3. The description adds the context that the query drives repo-count and star-sum calculations, but it does not provide additional syntax, formatting, or example guidance 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 clearly states what the tool does: it returns GitHub repo count and top-star sums for a search query. It frames the output as a developer interest/competition proxy, which adds meaning. It does not explicitly differentiate itself from siblings like github_trend, but the specific 'repo count and top-star sums' output is distinctive enough.

  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 the use case: measuring developer interest or competition via GitHub search. However, it gives no explicit guidance on when to prefer this tool over alternatives such as github_trend or hn_signal, and no exclusions or conditions are provided.

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