Server Quality Checklist

Tool Scores

• bh_discover_topicsC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It says the tool 'triggers' AI analysis, which hints at an asynchronous or launched process, but it does not explain whether this mutates state, how long it takes, whether results are returned immediately, or how failures behave.

  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 focused sentence that front-loads the core action and outcome. Every word contributes meaning, and there is no redundant filler or restating of the tool name.

  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?

  Without an output schema, the description should explain what the caller receives or how to retrieve results later. It only describes the trigger, leaving a gap: the sibling bh_get_topic_discoveries suggests results are stored or retrievable, but the agent is not told. This makes the definition incomplete for a tool that launches a multi-step analysis.

  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 of 3 is appropriate even though the tool description adds no parameter-specific detail. The description does not clarify how niche, targetAudience, and contentGoals relate to the Google Search Console analysis, but the schema already documents each parameter sufficiently.

  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 uses a specific verb ('Trigger AI analysis') and names a clear resource ('Google Search Console data') and outcome ('high-potential SEO topic opportunities'). It reads distinctly from read-oriented siblings like bh_get_topic_discoveries, though it does not explicitly distinguish itself from the similarly generative bh_generate_ideas.

  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?

  There is no guidance on when to choose this tool over alternatives such as bh_generate_ideas or bh_get_topic_discoveries. The intended context is implied by the description but not stated, and no exclusion criteria or follow-up steps are provided.

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

• bh_get_topic_discoveriesB
  3.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral burden. 'List' clearly indicates a read operation, but the description does not disclose pagination, ordering, result shape, or how filters behave. It is not misleading, but it is thin on behavioral detail.

  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?

  One concise, front-loaded sentence with no filler. Every word contributes meaning while leaving out unnecessary detail.

  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 two optional filter parameters, no annotations, and no output schema, yet the description only names the resource. It omits filter semantics, return-value shape, and sibling differentiation, leaving an agent to infer behavior that should be stated.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate for the two parameters, but it never mentions status or priority as filters. The enum values are somewhat self-explanatory, yet the description itself adds no parameter-level meaning.

  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 uses a specific verb ('List') and a clear resource ('topic opportunities'), with 'SEO-driven' adding useful context. It is distinct enough from obvious action tools like bh_discover_topics, though it does not explicitly name that sibling.

  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 the tool is for retrieving previously discovered topic opportunities, which gives a basic usage cue. However, it provides no explicit guidance on when to prefer this over alternatives like bh_discover_topics, nor does it mention the optional status and priority filters.

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

• bh_list_postsB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'List' and 'filter'; it does not mention default status behavior, pagination, ordering, or whether the operation is strictly read-only.

  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?

  A single sentence that front-loads the action and resource, with no filler. 'Optionally' efficiently signals both parameters are non-required.

  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?

  The tool is simple and both parameters are fully documented, but there is no output schema or annotations. The description does not clarify whether all statuses are returned by default or describe the response format, leaving some ambiguity for an agent.

  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?

  Input schema coverage is 100% with descriptions for both status and keyword, plus an enum for status. The description's 'filter by status or keyword' merely mirrors the existing schema descriptions, adding little value beyond the structured data.

  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 ('List') and resource ('blog posts'), and mentions optional filters. It is clearly distinct from siblings like bh_list_subscribers and bh_create_post.

  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?

  Provides no guidance on when to use this tool versus alternatives. It does not reference sibling tools or any exclusions; agents must infer that stats or creation belong elsewhere.

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

• bh_generate_ideasB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description carries the disclosure burden. It does disclose the key behavioral outcome: exactly 5 unique angles will be generated. It does not mention output format, nondeterminism, or whether the operation has side effects, but for a non-destructive brainstorming tool this is a reasonable baseline.

  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, front-loaded with the action and deliverable. 'using AI' is mildly redundant in context but does not distract from the core message.

  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?

  For a single-parameter tool with full schema coverage, the description is adequate to decide when to call it. However, with no output schema, it would benefit from a note about what the response looks like and how the five angles are presented.

  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%, and the only parameter, 'topic', is already described as 'Topic to brainstorm ideas about'. The description adds the 'blog post angles' context but does not need to compensate for missing schema information.

  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 verb ('Brainstorm'), a concrete deliverable ('5 unique blog post angles'), and the input type ('topic'). It is clear about scope, though it does not explicitly contrast with siblings such as bh_discover_topics.

  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?

  Usage is implied by the verb 'brainstorm' and the target 'blog post angles': use this when you need ideation for a topic. However, there is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named, so an agent has to infer when this is preferred over siblings like bh_discover_topics.

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

• bh_social_echoB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full responsibility for behavioral disclosure. It states what is generated but not whether anything is persisted, whether authentication or side effects are involved, or how the generated content is returned to the agent.

  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 no filler. Every word contributes to the tool's purpose, making it easy to scan and parse quickly.

  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 single-parameter generation tool, the description identifies both the input and the expected artifacts, which is reasonably complete. It loses a point because, with no output schema and no annotations, the return format and persistence behavior remain unstated.

  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 schema already describes the sole parameter, postId, as 'ID of the blog post' with 100% coverage. The description adds no semantic detail about the parameter beyond implying the blog post is the source content, so the schema does the necessary work.

  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 uses a specific verb ('Generate'), lists concrete resources ('Twitter thread, LinkedIn post, and newsletter teaser'), and scopes to 'an existing blog post'. This clearly separates it from siblings like bh_create_post or bh_generate_ideas, though it does not name those alternatives explicitly.

  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 establishes a clear prerequisite: the blog post must already exist, implying this is post-publication content generation. However, it does not state when to prefer this over siblings such as bh_generate_ideas or bh_create_post, leaving the usage decision partly to inference.

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

• bh_list_subscribersA
  3.7/5.0
  Behavior3/5

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

  The verb 'List' signals a read-only operation and indicates the result is a collection of subscribers, but with no annotations the description carries the full burden. It does not disclose output structure, pagination, privacy considerations, or whether the publication is contextually selected.

  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 clear sentence with no filler, redundancy, or tangential information. It front-loads the action and the resource, making it easy for an agent to parse quickly.

  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?

  For a zero-parameter tool this is mostly sufficient, but there is no output schema to clarify the return shape and no annotation to confirm safety. A brief note about which publication context applies or what fields appear in the subscriber list would make the definition more complete.

  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 and the parameter count is zero, so there are no parameters requiring documentation. The description correctly adds no unnecessary parameter detail, and the baseline for zero parameters 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?

  The description uses a specific verb ('List') and a unique resource ('newsletter subscribers') scoped to 'the publication,' making it clearly distinguishable from sibling tools like bh_list_posts and bh_get_stats. It adds information beyond the tool name without repeating it.

  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?

  There is no explicit guidance on when to use this tool versus alternatives, and no mention of exclusions or preferred contexts. The only usage signal is implied by the resource name, so the agent must infer when this is the right tool.

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

• bh_create_postA
  3.8/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral burden. It discloses that the tool is asynchronous: 'Returns a receipt immediately; post appears in dashboard within minutes.' It also reveals a processing pipeline (SEO brief → RAG evidence → BullMQ job). It does not cover failure modes, permissions, or what happens if both title and topic are supplied, but the key async behavior is well communicated.

  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 short and front-loaded with the core action. The pipeline chain 'SEO brief → RAG evidence → BullMQ job' is dense and jargon-heavy, which slightly weakens clarity, but it earns its place by explaining the AI generation behavior. Overall efficient and focused.

  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?

  The description conveys the primary workflow and async result, which is good for a create tool with no output schema. However, it leaves gaps around mode selection: there are no required parameters, so the agent could invoke with an empty object, and it is unclear whether title and topic are mutually exclusive. The absence of any expected receipt shape or error behavior further limits completeness for a moderately complex 7-parameter tool.

  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 explains every parameter. The description adds value by recommending 'topic' as the high-quality path and noting the async receipt, but it does not detail parameter interactions or format requirements beyond the schema. 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 is explicit: 'Create a blog post' names the action and resource. It distinguishes itself from sibling read/generation tools like bh_list_posts and bh_generate_ideas by framing creation as its core purpose. The mention of 'AI generation' versus manual creation adds useful scope without ambiguity.

  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 modes by recommending 'topic' for AI generation and leaving manual fields to the schema, but it never states when to choose manual versus AI generation. It also does not reference any sibling tool as an alternative or exclusion, such as using bh_generate_ideas first. The guidance is usable but mostly implicit.

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

• bh_get_statsA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the disclosure burden. It clearly indicates a read operation via 'Get' and names the returned data categories, but it does not disclose behavior such as time range, aggregation method, permissions, or whether the data is live or cached. This is minimal but not misleading.

  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 sentence with no filler, front-loading the action ('Get analytics summary') and then supporting details. Every word 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?

  For a zero-parameter analytics summary tool, the description is largely complete: it identifies the target publication and the expected content of the result. It does not explain the output format or time period, but those gaps are minor given the simplicity and absence of parameters.

  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 tool has zero parameters and the schema fully documents that with an empty properties object. The description does not need to add parameter-level meaning, and it does not attempt to, so the baseline score of 4 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 states a specific verb ('Get') and resource ('analytics summary'), and enumerates the included metric areas ('pageviews, subscribers, posts'). This clearly separates it from sibling listing/generation tools such as bh_list_posts or bh_generate_ideas.

  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 use when an analytics overview of the Bloghunch publication is needed, and the word 'summary' hints that it differs from listing individual posts or subscribers. However, it does not explicitly state when to prefer this tool over alternatives or mention any exclusions.

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