Server Quality Checklist

Tool Scores

• joinA
  3.6/5.0
  Behavior3/5

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

  The readOnlyHint annotation already covers the tool's non-mutating nature, so the description does not need to restate that. The description adds useful content scope—club definition, membership value, and starting point—but it does not describe the output format or any caveats. There is no contradiction with the annotations.

  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 compact sentence that lists three content areas in a sensible order: definition, benefit, and action. It is efficient and readable, though the title and description do overlap slightly on the idea of joining.

  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 zero-parameter, read-only, informational tool, the description gives enough context about the content an agent can expect. It could more explicitly say that the tool returns an explanation rather than performing a join, but the readOnly annotation and the wording make that interpretation reasonably clear.

  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?

  This tool takes zero parameters, so the input schema is empty and there is no parameter behavior to document. The description provides the necessary semantic context about what the no-arg call is about, which is sufficient.

  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 the tool as an informational resource about INITE Club, membership benefits, and where a principal starts the joining process. It is clearer than the bare name 'join' and the title adds context, but it never uses an explicit verb like 'returns' or 'explains,' and it does not differentiate itself from sibling tools.

  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 'what membership adds to what you can already do here' implies the tool is relevant when a user is weighing membership against existing access, and 'where your principal goes to start' implies a how-to-join scenario. However, there is no explicit statement of when to use this tool versus list_experts or ask_agent.

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

• list_expertsA
  3.6/5.0
  Behavior3/5

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

  The readOnlyHint annotation already declares the operation is safe, and the description adds useful context about principals being otherwise unreachable and agents being cheap to interrupt. It does not describe the return shape, whether the list is ordered, or how matching works beyond the schema's topic filter.

  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 compact sentences carry the entire definition with no filler. The first sentence states what the tool lists, and the second explains why the list is valuable.

  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 read-only filtered list, the description plus schema covers the core needs: what is listed, why it matters, and how to filter. A small gap remains because there is no output schema and the description only implies the return shape rather than stating it explicitly.

  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 only parameter, topic, has schema coverage of 100% with the description 'Only agents that cover this topic.' The tool description adds no additional parameter-level meaning or examples, so it relies appropriately on 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 identifies the resource being listed (club members whose agents answer outside questions) and the content of each entry (what each will talk about). It does not explicitly contrast this with the sibling tools join and ask_agent, so it stops short of full sibling differentiation.

  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 title 'Who you can ask' and the note that their agents cost nothing to interrupt imply this tool should be used to find an expert before asking one. However, it never explicitly states when to use list_experts versus ask_agent or join, so the guidance remains implicit rather than direct.

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

• ask_agentA
  4.2/5.0
  Behavior4/5

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

  The description goes beyond annotations by disclosing that the answer is mandate-bound, runs in an isolated context with no tools, and that the quota on questions is limited. Even though readOnlyHint is false, this is consistent because asking consumes one of a limited number of questions. It does not contradict annotations and adds useful behavioral context.

  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 well-crafted sentences with the core action front-loaded and every clause carrying meaning: isolation, no tools, mandate-bound, non-committal, and limited quota. There is no redundant wording or repetition of schema details.

  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 3-parameter, no-output-schema tool, the description covers purpose, constraints, and behavior fully. 'The answer comes whole' addresses the return shape enough. A small gap is that it never states what happens when the limited question count is exhausted, but that is not essential for calling the tool once.

  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 the schema already documents memberId, topic, and question adequately. The description only reinforces the 'one question' idea and does not add new meaning to any individual parameter. Baseline 3 is appropriate.

  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 opens with 'Put one question to a member's agent', a specific verb-plus-resource statement that clearly identifies the tool's function. The title 'without joining' and the line 'it cannot agree to anything on their behalf' distinguish it from the join sibling, so an agent can tell them apart.

  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: this is for one-off informational questions, answered in isolation with no tools, and cannot produce commitments. The phrase 'it cannot agree to anything on their behalf' implies that for agreements the agent should look at join, though join is not explicitly named. It lacks an explicit when-not-to-use statement, so it falls short of a 5.

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