Server Quality Checklist

Tool Scores

• upsert_lead_profileA
  3.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of disclosing behavior. It reveals the internal operations (upsert Company, upsert Contact, associate), idempotency, return value (IDs), and error handling (bad data recorded and reported, never silently dropped). This is comprehensive for safety and side effects.

  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 three sentences, each earning its place: first sentence defines the action, second sentence emphasizes idempotency, third sentence covers error handling and return values. No redundancy or unnecessary detail.

  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 adequately covers purpose, safety, and error behavior, and the output schema covers return values. However, given the high parameter count (10) and zero schema descriptions, the lack of parameter guidance leaves the description incomplete for correct invocation. It is sufficient for understanding what the tool does but not for parameter selection.

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

  Parameters1/5

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

  Schema description coverage is 0%, and the description does not explain the purpose or format of any of the 10 parameters (e.g., what employee_id, company_id, decision_maker_flag represent). The description must compensate for the lack of schema parameter descriptions, but it fails to do so, leaving the agent to guess parameter semantics from names alone.

  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 action ('Create or update one lead'), the resource ('lead in HubSpot'), and specifics that it upserts both Company and Contact and associates them. It distinguishes itself from sibling tools like 'get_lead_profile' (read-only) and 'upsert_blog_summary' (different entity).

  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 explains that calling the tool twice is safe and does not duplicate, indicating idempotency. However, it does not provide explicit guidance on when to use this tool versus alternatives (e.g., get_lead_profile for reads) or when not to use it, leaving usage context implied.

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

• get_lead_profileA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden for behavioral disclosure. It covers read-only safety, enumerates the returned fields, and explains the company_resolved flag and warnings. This is substantial context for a read tool, though it does not cover error cases or edge behaviors in 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?

  The description is two sentences with no redundancy. The first sentence states the core purpose and safety, and the second adds essential behavioral details. Every word contributes value.

  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 tool with an output schema, the description covers the main aspects: purpose, return fields, and a key data-quality flag. However, it omits parameter usage, which is a notable gap given the low schema coverage. The output schema likely documents return values, so that is not a deficiency.

  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. It does not mention email or employee_id at all, nor explain how the lead is identified, whether identifiers are mutually exclusive, or what happens if neither is provided. The schema only provides types and defaults, leaving the semantic meaning entirely unexplained.

  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 function: 'Read one lead's current state from HubSpot.' It uses a specific verb and resource, and explicitly declares read-only behavior. It differentiates from siblings by focusing on leads rather than blog summaries and by contrasting with upsert operations.

  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 implies usage context by stating the returned IDs are 'so you can write status back without re-searching,' suggesting it is the read-before-write companion to upsert_lead_profile. It also instructs to check company_resolved for interpreting data. However, it does not explicitly name alternatives or provide 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.

• get_blog_summaryA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description takes full responsibility for behavioral transparency. It clearly states the tool is read-only, describes the return fields and the non-error 'not-found' behavior, and warns about potential ambiguity with shared timestamps. The only minor omission is not specifying the exact return structure or whether it includes pagination.

  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 four sentences, each with distinct value: purpose, safety, error handling, and edge-case warning. It is front-loaded with the core action, no wasted words.

  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 simple single-parameter tool and presence of an output schema (which handles return structure), the description covers purpose, behavioral edges, and warnings adequately. The omission of timestamp format detail is minor and acceptable for a tool with just one parameter and no nested objects.

  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 0%, so the description must compensate. It explains that the single parameter 'blog_published_at' is a publication timestamp for identifying the row, which aligns with the schema. However, it does not provide format details (e.g., ISO 8601) or validation constraints beyond that, leaving the agent to infer from context.

  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 specifies a clear verb ('read'), a specific resource ('blog summary row'), and the unique identifier ('publication timestamp'). It also distinguishes from siblings like 'upsert_blog_summary' and 'get_lead_profile' by focusing on reading a blog summary.

  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 provides context on when to use this tool: reading a single blog summary by timestamp. It does not explicitly mention when not to use it or alternatives, but the sibling list and the read-only nature imply a contrast with upsert_blog_summary. Some guidance on the 'not-found' and 'warnings' behavior aids correct usage.

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

• upsert_blog_summaryA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and excels: it reveals the upsert logic (no duplicates), mentions the return value (ticket id and created/updated status), warns about exact value requirements for blog_industry, and states that bad data is recorded and reported as failed. This is comprehensive behavioral disclosure beyond what any annotation could provide.

  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 compact, every sentence adds critical information, and key points are front-loaded. It covers purpose, safety, return value, parameter constraints, and error handling without redundancy.

  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?

  Given the tool has 5 parameters, an output schema, and no annotations, the description provides all necessary behavioral context including upsert semantics, exact enum values, and failure behavior. The return value is described, and the output schema structure is implied but not needed in detail. This is complete for an agent to use the tool correctly.

  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 schema has 0% description coverage, so the description must compensate. It explicitly explains the blog_industry parameter's allowed values and failure behavior, and implies the meaning of blog_published_at as the search key. It does not detail subject, blog_summary, or summary_ref_id, but the overall intent is clear enough given the tool's purpose.

  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 puts a blog post into HubSpot using an upsert strategy, specifies it is the only writer to the blog summary store, and distinguishes itself from siblings by focusing on blog summaries rather than lead profiles. The verb 'put' combined with 'published blog post' and 'upsert' gives a concrete, specific purpose.

  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 states this is for published blog posts and mentions that calling it twice is safe due to upsert behavior. It does not explicitly list when not to use it or name alternatives among siblings, but the sibling tools (upsert_lead_profile, get_lead_profile, get_blog_summary) have different focuses, so the usage context is clear enough.

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