Server Quality Checklist

Tool Scores

• wire_searchA
  3.5/5.0
  Behavior5/5

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

  It goes beyond the readOnly/openWorld annotations by explaining that only the server's archive is searched, that '0 hits' does not mean absence in the world, and that Chinese/Russian content is indexed in its original language. It also tells the agent to retry transliterated or translated queries before concluding anything.

  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 compact, front-loaded with the core purpose, and uses a clear IMPORTANT warning for the most critical limitation. Every sentence adds necessary operational context without repetition.

  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?

  It fully covers the search scope and result interpretation, and the output schema covers return shape, but it omits parameter semantics and does not route the agent among sibling tools. For a 5-parameter search tool, this leaves some practical gaps.

  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, but it only implies the meaning of 'query' through phrases like 'If a query comes back empty.' It never explains days, sources, max_tokens, or limit_per_source, leaving the agent to guess their behaviors and interactions.

  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 opening sentence names a specific operation and resource: searching archived headlines across every source that carried a story. It clearly distinguishes archive search from a live feed, though it never names sibling tools explicitly.

  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 when-to-use versus alternative guidance; it does not mention wire_latest, wire_read, or wire_sources or state which tool to choose for current headlines or reading articles. The retry/transliteration advice is about query formulation, not tool selection.

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

• wire_sourcesA
  4.2/5.0
  Behavior4/5

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

  Annotations already mark the operation read-only and open-world. The description adds valuable interpretive context: absence of data may mean a source was never polled, not that it is empty, and it surfaces failing sources. This goes beyond what the annotations alone convey.

  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 with no filler. The first sentence front-loads the catalogue and health facts; the second adds a concise, important usage caution. Every sentence earns its place.

  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?

  For a zero-parameter read-only tool with an output schema and open-world annotation, the description fully covers why an agent would invoke it and how to interpret one of its key signals. Nothing essential is missing.

  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 baseline for this dimension is 4. There is no parameter ambiguity for the description to resolve, and no additional parameter meaning is needed.

  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?

  Describes the resource ('the catalogue and its health') and the specific facts it exposes: which sources exist, language, tags, last-answered time, and failing status. It is distinguishable from content-focused siblings like wire_read or wire_search, though it lacks an explicit action verb such as 'list' or 'retrieve'.

  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?

  Gives an explicit use case: 'Read this before concluding a topic is quiet.' It also warns about the distinct meaning of a never-polled source versus one with no content. It does not name alternatives or state when not to use the tool, but the context is clear.

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

• wire_latestA
  4.5/5.0
  Behavior5/5

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

  Beyond the readOnly/openWorld annotations, it explains DOWN means unknown rather than no activity, CUT indicates truncation, CROSS is arithmetic and not a ranking, ordering is not importance, and teasers are marked and are not the article. This is exactly the behavioral nuance an agent needs.

  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 dense but every sentence earns its place, with the core purpose front-loaded and caveats organized into digestible paragraphs. It avoids filler while covering crucial edge-case meaning.

  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?

  For an optional-parameter read tool with an output schema, it covers the domain caveats, the headline/full modes, language coverage, and how to proceed to wire_read. An agent can call it safely with defaults or with an informed detail/limit_per_source choice.

  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 carries the burden. It explains detail values and the effect of raising limit_per_source, but it leaves hours, since, sources, and max_tokens to their schema properties with no added semantics beyond 'time window'.

  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 opening states precisely what the tool returns: recent dispatches from 19 tech/AI sources in a time window, grouped by source and ordered newest-first within each. It also distinguishes itself by language scope and by positioning wire_read as the follow-up for article text.

  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 gives clear usage context: this is a date-only, unranked view and the CROSS metric is an early-signal indicator, not a ranking. It names wire_read for the next step, though it does not explicitly contrast with wire_search or state when to choose wire_latest over it.

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

• wire_readA
  5/5.0
  Behavior5/5

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

  Beyond the readOnlyHint and openWorldHint annotations, the description discloses two important behaviors: body=teaser is truncated and must not be used for conclusions, and missing IDs are named in the reply rather than silently dropped. 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.

  Conciseness5/5

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

  Three sentences with no filler: first states the purpose, second delivers a critical caveat, third explains missing-ID behavior. Each sentence adds essential information and the most important usage guidance is front-loaded.

  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 a simple one-parameter signature, an existing output schema, and annotations covering read-only behavior, the description covers all remaining ambiguity: how IDs are obtained, the teaser truncation trap, and recovery steps for stale IDs. Nothing important is missing.

  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 coverage is 0%, so the description carries the full burden for the 'ids' parameter. It explains that IDs come from wire_latest or wire_search and describes what happens when IDs are not in the archive, giving the agent enough context to supply valid 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 states it retrieves stored text of specific dispatches by IDs returned from wire_latest or wire_search, which clearly identifies the operation and distinguishes it from the sibling list/search tools. The title 'Read dispatches' reinforces the verb and resource.

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

  Usage Guidelines5/5

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

  It explicitly instructs the agent to supply IDs returned by wire_latest or wire_search, and advises re-running those tools if IDs are stale or missing. It also warns not to treat teaser text as the full article, providing clear contextual guidance.

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