Server Quality Checklist

Tool Scores

• brainstormC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of disclosing behavior. It states that multiple experts will think divergently, but it doesn't explain how many experts participate, how the process works, whether the output is a list of ideas, or any caveats like dependency on the topic or constraints. The agent cannot anticipate the outcome beyond 'innovative ideas'.

  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, succinct sentence that communicates the core purpose without verbosity. It is front-loaded with the key concept (brainstorming) and the mechanism (multiple experts). It could have added a bit more detail without becoming lengthy, but as a standalone it is efficient.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with no output schema and no annotations, the description is too sparse. It doesn't specify what the agent should expect in the response (e.g., a structured list of ideas, a summary), and it doesn't explain the optional advisors/constraints behavior, such as how a default expert set is chosen. An agent would need to infer or experiment to understand the full workflow.

  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% – all three parameters (topic, advisors, constraints) have descriptions in the schema itself. The description adds no extra parameter information, so the baseline of 3 is appropriate. It doesn't clarify the default selection behavior for advisors, which the schema implies but doesn't specify.

  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 states 'brainstorming' (头脑风暴) with multiple experts diverging from different angles to generate innovative ideas. It specifies the verb, resource (multiple experts), and the creative outcome. It doesn't explicitly differentiate from sibling tools like roundtable or consult, but the purpose is unmistakable and not a tautology.

  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?

  No guidance on when to use this tool versus siblings such as roundtable, consult, or review. There is no mention of when brainstorming is appropriate, nor exclusions for cases where a different approach (e.g., structured critique) would be better. The description is purely a capability statement.

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

• critiqueC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description must fully disclose behavioral traits. It only states that the tool critiques and finds problems, but does not mention that it can simulate multiple expert advisors (as indicated by the 'advisors' parameter), how detailed the critique is, whether it is read-only, or what the output format looks like. These gaps leave the agent uncertain about expected side effects and output structure.

  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, concise sentence that conveys the core purpose. It is front-loaded with the main action and goal. However, it is slightly terse and could mention the optional experts or dimensions without becoming verbose. It earns a 4 because it is efficient but not maximally informative.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has three parameters including a complex enum of 38 expert advisors, yet the description does not explain what the 'advisors' parameter does or how it affects the critique. There is no output schema, so the description should at least hint at the output structure. The description is too minimal for this tool's richness, leaving significant gaps for an agent to infer.

  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 input schema covers all parameters with descriptions (100% coverage). The description does not add parameter-level semantics, but since the schema already documents 'design' as the input and 'advisors' and 'dimensions' as optional lists with enumerated values, the baseline of 3 is appropriate. It adds no extra meaning but does not need to.

  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 states the tool's purpose: critically evaluate a design from multiple dimensions to identify problems and improvements. It uses a specific verb ('审视' - examine) and resource (方案 - proposal), but it does not distinguish itself from sibling tools like 'review' or 'consult' that may have overlapping purposes.

  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?

  No guidance on when to use this tool versus alternatives such as roundtable, consult, review, brainstorm, or suggest. The description implies it is for design review but provides no exclusions or conditions that would help an agent choose between this and similar tools.

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

• suggestB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden, and it only states that suggestions are produced. It does not disclose the notable advisor-selection behavior (the advisors parameter lists named experts/figures), nor how constraints influence the output, nor what the returned suggestion looks like.

  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?

  One short sentence with no filler; the main action is front-loaded. It is slightly repetitive with the '场景建议' label, but the definition is compact and easy to scan.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has no output schema and no annotations, and the description gives no insight into output format, advisor behavior, or how to choose among the sibling tools. For a 3-parameter tool with a distinctive expert-list parameter, this is inadequate.

  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 scenario and constraints; the description echoes '场景和约束条件' without adding detail. The meaningful advisors parameter is present in the schema but not addressed in the description, though the schema's enum and label at least name it.

  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 a clear action – give executable solution suggestions based on a scenario and constraints – and is not a tautology. However, it does not distinguish this 'suggest' tool from siblings like consult, brainstorm, or roundtable, all of which plausibly produce suggestions.

  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?

  It implies when to use it: when there is a concrete scenario and constraints requiring actionable advice. But it gives no explicit when-not-to-use conditions and does not mention any alternative tool, so an agent must infer where it fits among the sibling tools.

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

• reviewA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description clarifies the core behavior: multiple experts review from different angles and produce comprehensive advice, so the agent knows this is an advisory/read-only style operation. It does not disclose what happens when no advisors are specified, how focus affects the output, or the exact output format.

  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 a single, front-loaded sentence with a clear label ('多角色会诊') followed by the behavior and outcome. There is no filler or redundancy; every part 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?

  The schema covers all parameters, and the description clearly communicates the expected output ('提供综合建议'). Since there is no output schema, this is enough for an agent to know what it will receive. The main gaps are unspecified default behavior when 'advisors' is omitted and the exact structure of the combined advice.

  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%; all three parameters (proposal, focus, advisors) already have rich descriptions in the schema. The tool description adds no additional parameter semantics, which is acceptable given the schema coverage, but also means it provides no extra value beyond 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 names a specific action ('评审方案' - review a proposal) and a clear resource (方案/设计/代码, reinforced by the schema). The '多角色会诊' framing makes the multi-expert purpose explicit, which helps distinguish it from generic tools. It does not explicitly contrast itself with the sibling tool 'roundtable', which could serve a similar multi-perspective role.

  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 description implies usage: when a proposal exists and multiple expert perspectives are wanted. However, it does not state when to prefer this tool over alternatives such as 'roundtable', 'consult', or 'critique', and it gives no explicit when-not-to-use guidance.

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

• consultA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool returns advice from an expert, but it gives no detail on response format, limitations, side effects, or any behavioral nuance beyond that basic promise.

  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 extremely concise: two short sentences with no filler. The core action is front-loaded, and every phrase serves a purpose.

  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 advice tool with no output schema, the description conveys the essential call pattern: select a single expert and ask a question. Optional context is documented in the schema. It omits guidance on which expert to choose or what the response will look like, but these are minor gaps for a tool of this simplicity.

  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 baseline is 3. The description only loosely maps to parameters ('choose an expert' to advisor, 'ask a question' to question) and does not add extra meaning or usage detail for the parameters beyond what the schema already provides.

  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 a specific action and resource: '向智囊团中的单个专家咨询问题' (consult a single expert in the think tank). It also distinguishes itself from group-oriented siblings by emphasizing '单个专家' (single expert), making its scope clear.

  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 description implies usage when a single expert perspective is needed, but it does not explicitly name alternatives or state when not to use this tool. Guidance is left to inference rather than being stated directly.

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

• roundtableA
  4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full responsibility. It discloses key behaviors: automatic triage by desk type, selection of 3-5 advisors, rotating speaking contract, and uniform meeting minutes output. Adds context about decision routing beyond what a plain 'run a meeting' would say.

  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 clear sentences, front-loaded with the core purpose and mechanism. Every clause adds value: triage logic, advisor count, speaking contract, output format, and the 'no manual selection' advantage. No filler or redundant wording.

  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 the tool has 3 params (1 required), an enum, and no output schema, the description covers the main usage: what question types are acceptable (career/tech/product/life), how desk selection works, and the output (meeting minutes). Minor gaps: the exact format of 'uniform meeting minutes' isn't specified, and no mention of any limitations like token limits, but overall sufficient for an agent to understand its function.

  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 parameters already well-described (desk enum values and their meanings, context purpose, question content). The description adds only the triage logic for desk selection (day=career/tech, night=life), which duplicates the schema's desk parameter description. No significant additional meaning beyond the schema.

  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?

  Description states a specific verb (召开) and resource (圆桌会议), and explicitly differentiates from siblings by mentioning automatic triage (白天桌=事业/技术决策, 夜晚桌=人生探讨) and the fact that users don't manually select experts. It clearly distinguishes this from consult or brainstorm 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?

  Implicit guidance via '用户无需手动挑选专家' suggests automatic expert selection, but there's no explicit when-to-use or when-not-to-use statement nor named alternatives. Sibling comparison is only implied.

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