Server Quality Checklist

Tool Scores

• verified_searchA
  4.6/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so excellently. It reveals the critical safety mechanism: every item's source field is validated in code against literal search-result URLs, and unverifiable items are dropped rather than hallucinated. It also discloses that the model restructures ONLY what the search actually returned. This is exactly the kind of behavioral detail an agent needs to trust and safely invoke the tool.

  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 — three sentences — and each one earns its place. It front-loads the primary purpose, then explains the safety/verification mechanism, and finally gives actionable usage instructions. There is no filler or repetition of schema details that are already present.

  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 nested parameters, no output schema, and no annotations, the description covers the core workflow thoroughly: what it does, how it prevents hallucination, what inputs to provide, and how sourceField is auto-added. The only notable gap is the absence of an explicit description of the return format (e.g., whether it returns a bare array of items or a wrapped object). Still, the description mostly implies the output shape via 'restructure ... into the JSON shape you specify,' making it adequate.

  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?

  Schema description coverage is 100%, so the schema already documents all parameters with examples. The description adds key semantic value beyond the schema: it explains that 'sourceField, default "sourceUrl", is added automatically if you don't include it' — which clarifies an important behavior not fully specified in the schema. It also frames itemSchema as the target shape for restructured results, linking the parameter to the tool's core workflow.

  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 specifies a precise action: 'Finds real things matching a query' by running a real web search and restructuring only returned results into a user-specified JSON shape. The verb is clear, the resource is well-defined ('real things' — products, opportunities, tickets, etc.), and the description distinguishes the tool's core verification behavior from a generic search or extraction tool. Even without siblings, the purpose is 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?

  The description gives clear context for when to use this tool: whenever an agent needs real, verifiable web results converted into a structured JSON shape. It also provides practical instructions — 'Give it a plain-language query and a JSON Schema for one result item.' However, it does not explicitly state when NOT to use it or name alternative tools, though no siblings are listed. This is a clear-context-without-exclusions case.

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