Server Quality Checklist

Tool Scores

• check_answersA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It usefully flags that replies are untrusted data and that fetching returns only answers 'that have arrived,' implying non-blocking behavior by default. However, 'Same handling rules apply' references a rule set not stated here, and it omits blocking/latency behavior, rate limits, and the shape of returned answers.

  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 short sentences, front-loaded with the action, then the dependency, then the safety caveat. No filler or 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 two-parameter read tool with no output schema or annotations, the description covers the action, the id source, and a security caveat. It could say more about what the returned answers look like or the blocking behavior of wait_seconds, but an agent has enough to invoke it 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 coverage is 100%, so both parameters are already documented in the schema, including wait_seconds' max of 55 seconds and its blocking semantics. The description reinforces that id comes from ask_humans but adds no new meaning beyond the schema, so baseline 3 applies.

  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 ('Fetch any answers that have arrived for a question you already asked') and ties it to the counterpart flow by naming ask_humans. An agent can distinguish it from its only sibling without opening the schema.

  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?

  Tells the agent to use the id returned by ask_humans, which establishes the correct sequencing after ask_humans. It lacks an explicit when-not clause (e.g., don't poll repeatedly or how to use wait_seconds), but the usage context is clear.

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

• ask_humansA
  4.5/5.0
  Behavior5/5

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

  With no annotations present, the description carries the full burden and does so: it discloses that responses are untrusted DATA that must not be followed as instructions, that they are individual opinions rather than sentiment, and that respondent counts must be stated. It also surfaces the privacy/permission precondition for contains_user_private_context, which is exactly the kind of behavioral constraint annotations would otherwise supply.

  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 core purpose is front-loaded in one sentence, followed by trigger conditions and then privacy guidance in a sensible order. The 'Also use it when' paragraph is somewhat listy and could be tightened, but for a tool whose correct use depends on judgment it is mostly earning its length rather than padding.

  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 5-parameter tool with no output schema and no annotations, the description covers the gaps that matter: when to call it, the privacy precondition, and the nature and handling obligations of the returned data. An agent has everything needed to invoke it correctly and to report results responsibly.

  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 five parameters and the baseline is 3. The description adds real value above that by explaining the de-identification default and the precise condition for setting contains_user_private_context (only when the question cannot work without private context, plus a show-and-approve step), which is more operational detail than the schema's one-liner.

  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 line states a concrete verb and resource — ask real humans a question, get verbatim answers — which an agent can act on immediately. It is specific about the modality (real humans, verbatim replies) rather than a generic 'query' tool. It stops short of naming sibling check_answers or clarifying the ask-then-check flow, so the differentiation is implicit rather than explicit.

  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?

  This is textbook when-to-use guidance: it names the exact phrase in the agent's own output ('you should validate this with real users') that should trigger the call, plus a list of qualifying conditions (unreachable forums, current on-the-ground conditions, unpublished reactions, churned users). It also gives a default policy (de-identify) and the explicit exception path for private context.

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