Server Quality Checklist

Tool Scores

• check_tokenA
  3.7/5.0
  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 adds genuine context — automatic renewal within the 7-day window and the re-authorization fallback — which helps the agent interpret results. Still, the tool's own operational traits (read-only, no side effects) are only implied by the verb '查看' rather than stated.

  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 clauses front-load the core purpose and then add only high-value lifecycle facts. Every sentence earns its place; there is no filler or repetition of schema content.

  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, no-output-schema check tool this is nearly complete: the description states what is reported (remaining days) and explains the surrounding token policy. It could add a brief note on the exact return format, but nothing an agent needs to call the tool is missing.

  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?

  The input schema is empty (0 parameters, 100% coverage), so there is nothing for the description to document. Baseline 4 applies: no parameter ambiguity exists, and the description confirms the tool only inspects token state.

  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 opens with a specific verb and resource — '查看访问令牌剩余有效天数' (check the remaining valid days of the access token) — so an agent immediately knows what the tool does. The 60-day expiry and auto-renewal context helps place it in the token lifecycle and implicitly set it apart from siblings like refresh_token, though it never names the alternatives.

  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 lifecycle information ('60 天过期', '剩余 7 天内自动续期', '彻底过期则只能重新授权') implies when checking token health matters and hints that renewal is handled automatically. However, there is no explicit guidance on when to use this tool versus refresh_token or get_publishing_limit — no direct exclusions or alternative routing.

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

• refresh_tokenA
  3.7/5.0
  Behavior2/5

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

  没有注解，描述承担全部责任。它揭示了自动续期行为和有效期重置，但未提及可能的副作用、权限要求、频率限制或幂等性，行为透明性不足。

  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?

  两句话简明扼要，关键信息（续期、60天、自动）前置，无冗余内容，结构高效。

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

  Completeness3/5

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

  对于无参数、无输出schema的简单工具，描述提供了核心行为和默认调用场景，但缺少手动调用的必要场景说明，完整性略有欠缺。

  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?

  此工具没有参数，schema覆盖率为100%，描述无需额外解释参数。无参数的工具基线为4，符合要求。

  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?

  描述明确说明了操作是'续期访问令牌'，并给出了具体效果（有效期重置为60天），动词和资源清晰，与兄弟工具（如check_token）形成区分。

  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?

  描述提到'通常不必手动调用'，暗示了非使用场景，但没有说明何时需要手动调用或提供替代方案。虽有一定指引，但不够完整。

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

• get_publishing_limitA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description bears the full burden. It discloses the key behavioral detail: the exact quota window and counting rule, which is useful. However, it does not state whether the operation is read-only, what the return value looks like, or any side effects. The description is partially transparent but lacks return-format and safety 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?

  The description is a single, compact sentence that packs the necessary quota information and usage trigger into minimal words. Every phrase is informative: the quota value, the rolling window, the carousel counting rule, and the use case.

  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 discovery tool, the description provides the essential facts: quota limit, time window, and when to invoke. The lack of return-value specification is a minor gap since the operational context is otherwise clear. The description is complete enough for an agent to successfully use the tool.

  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 has zero parameters, so the baseline is 4. The description correctly focuses on the quota details rather than parameter explanations, which are unnecessary. The description adds value by explaining the quota semantics that would otherwise be opaque.

  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 clearly states the tool's purpose: retrieving Instagram's publishing quota with specific details (100 posts per 24-hour rolling window, carousel counts as 1). It uses the verb '查' (check) and names the exact resource, making it distinct from siblings which handle publishing and token management.

  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 explicitly says to check this when publishing failures are suspected to be caused by rate limiting, providing a clear when-to-use. It does not mention when not to use it or alternatives, but for a simple quota lookup this guidance is sufficient and actionable.

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

• publish_postA
  4.6/5.0
  Behavior4/5

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

  Although no annotations are provided, the description discloses important behavioral traits: the server actively pulls media from public https URLs, local/intranet paths won't work; image cropping based on first image's aspect ratio; carousel ordering defines display order; pure text rendering (no Markdown). These are non-obvious behaviors that help avoid failed calls. A small gap: it doesn't mention what the response looks like or potential side effects (e.g., posting immediately).

  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 dense but well-structured: it front-loads the core purpose, then breaks constraints into a compact list of requirements. Every sentence provides actionable information with no fluff. It's long but justified because of the numerous technical constraints; clarity is maintained.

  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 publishing tool with no annotations or output schema, the description covers input constraints comprehensively, the behavior of media fetching, and likely failure modes (e.g., local paths won't work). It lacks explicit return-value or error-handling info, but since there's no output schema, the description carries that burden; still, it's sufficiently complete for an agent to invoke correctly. Sibling context shows it's part of an Instagram integration, so no further context is needed.

  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 baseline is 3. The description adds significant meaning beyond the schema strings: it explains that image_urls must be publicly accessible https URLs (server fetches them), 1-10 images, JPEG, size limits, dimensions, and aspect ratios; alt_texts correspond one-to-one; caption length and pure-text behavior. This compensates and elevates above baseline.

  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 clearly states the tool's purpose: publish images/text to an Instagram professional account. It specifies the resource (Instagram professional account) and action (publish), and differentiates itself from sibling tools like get_publishing_limit, check_token, and refresh_token, which are about authorization or limits, not publishing content.

  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?

  The description explicitly states when to use this tool (to publish single or carousel posts) and what constraints apply (image format, size, dimensions, aspect ratio, caption length, hashtag limits). It also implies not to use it for other Instagram operations such as fetching limits or managing tokens, which are handled by sibling tools. This is clear usage context.

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