Server Quality Checklist

Tool Scores

• statusA
  4/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It discloses that probe pings backends, but doesn't detail what the probe does when failures occur or the exact output structure. It does mention cooldowns and last errors as return content, which is useful. There's no contradiction with annotations since none exist.

  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: purpose, key optional behavior, and usage context. Front-loads the main purpose and then adds actionable guidance. No wasted words—every sentence earns its place.

  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 an output schema exists (not described in detail but signaled), the return value structure need not be explained. Tool complexity is moderate (3 optional params, one boolean). The description explains when to use it and what to check for. It could mention what happens if probe=true and backends fail, but since it focuses on diagnostics, this is adequate. Sibling 'search' is the only other tool, and status is clearly distinct.

  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%, with 'probe', 'target', and 'targets' all described in the schema. The description mentions 'Optional probe pings backends' which aligns with the probe field but doesn't add much beyond the schema. It also implies target/targets are optional, consistent with schema defaults. Baseline 3 applies since schema already documents parameters fully.

  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?

  Clear verb ('Show') and resource ('ddg-search backend router status'). Distinguishes itself from sibling 'search' by explicitly targeting the router health, cooldowns, and errors—a diagnostic role that search does not play.

  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?

  States when to use it ('after search failures') and gives a conditional directive ('if last_error is local/transport, fix the workstation...'). Doesn't explicitly rule out other scenarios, but provides useful decision context. Sibling 'search' is clearly the alternative primary action tool.

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

• searchA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description must carry the behavioral burden. It discloses the local+remote backend split, that it's read-only discovery, and decodes error tags to distinguish local vs remote failures. It does not mention rate limits, caching, or concurrency behavior, but for a search tool it covers the most critical operational behaviors.

  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 dense paragraph, but every sentence adds value: purpose, follow-up action, routing modes, and failure decoding. It is slightly long but not verbose; front-loads the core purpose before details. Could be improved with bullet points but is acceptable.

  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 6 parameters (1 required), an output schema exists (not shown), and helper sibling 'status', the description covers all necessary operational context: what it returns (titles/URLs/snippets), when to use each route mode, how to interpret failures, and the follow-up tool (fast-webfetch). Nothing essential is missing—an agent could call this tool correctly without further clarification.

  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 baseline is 3. The description does not add meaning beyond the schema; it repeats the routing guidance already in route_mode and the query tips already in the query parameter. The extra notes about backend combinations and error tags are behavioral rather than parameter-specific, so no increment.

  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?

  States a specific verb and resource: 'Search DuckDuckGo via ddg-search'. It clearly delimits scope with 'Discovery only — titles/URLs/snippets, not page proof', distinguishing it from follow-up fetch tools and giving an agent an unambiguous sense of what it returns and what it does not.

  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?

  Provides explicit routing rules: 'auto = healthy low-use backends; manual = target/targets' and tells when to use manual mode. It also instructs on failure interpretation: 'read Attempts tags' with specific meanings for [empty], [local]/[local-transport], [remote-rpc]/[remote-tool-error], and [timeout]. This is actionable when-to-use and how-to-handle guidance.

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