Server Quality Checklist

Tool Scores

• check_domainA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, establishing a safe read operation. The description adds valuable behavioral context: grading (A-F), fixes for problems, default summary vs. section drill-down, and the domain-not-email constraint. No contradiction with annotations.

  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?

  Three sentences, front-loaded with the primary function, followed by use cases and input/behavior details. No wasted words; each sentence 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 tool is complex (multiple sections, grading, fixes), but the description covers scope, output style (grades, fixes), and navigation (section parameter). With no output schema, it doesn't spell out return format in detail, but it still conveys sufficient behavior for a read-only domain audit.

  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 already covers all three parameters with descriptions (100% coverage). The description goes beyond the schema by clarifying that 'domain' must be a domain, not an email address, and explaining how 'section' changes output (summary vs. full records). This adds meaningful semantic contrast.

  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 the specific verb 'Audit' and resource 'a domain's email setup', enumerating concrete checks (MX, SPF, DKIM, DMARC, etc.). It clearly distinguishes itself from siblings like validate_email and check_spf by covering the entire domain setup rather than a single email or SPF record.

  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?

  Provides explicit use cases ('can this domain send and receive mail', 'why do our messages land in spam') and an exclusion ('takes a domain, not an email address'). While it doesn't name alternative sibling tools, the intended context is clear.

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

• check_spfA
  4.5/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true, so safety is already covered. The description adds behavioral context by specifying what analysis is performed (mechanisms, lookup count, misconfigurations), going beyond the annotations without any contradiction.

  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 sentences, front-loaded with the primary action and outputs, followed by a clear alternative. No redundant words or unnecessary details.

  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?

  For a single-parameter read-only tool, the description fully covers what it does, what it returns, and when to prefer an alternative. No output schema is present, but the description enumerates the return components.

  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 a parameter description for 'domain' already present. The description does not add further parameter semantics beyond the schema, so the baseline score of 3 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 ('Fetch and analyse') and resource ('SPF record of a domain'), and lists concrete outputs (raw record, mechanisms, lookup count, common misconfigurations). It also explicitly contrasts with check_domain, making its purpose distinct from siblings.

  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 check_domain instead ('when the question is about overall deliverability'), providing a clear alternative and exclusion criterion for usage.

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

• validate_emailsA
  4.5/5.0
  Behavior5/5

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

  The description goes well beyond the readOnlyHint annotation by explaining that Unknown means the mailbox could NOT be checked due to specific causes, that the call is slow by nature, requires an API key with a 25-address free limit, and that parallel calls fail. These are behavioral traits not captured in 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is longer than average but every sentence serves a distinct purpose: purpose, Unknown semantics, API key, performance, and concurrency. It is front-loaded with the primary function in the first sentence and structured logically, earning its length.

  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's complexity (batch validation with nuanced Unknown handling and concurrency limits), the description covers all operational aspects: usage, auth, performance, and result interpretation. The output schema covers return details, so the description complements it well.

  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 fully documents the only parameter 'emails' with description 'The addresses to check, at most 50 per call' (100% coverage). The description's mention of 'up to 50' repeats the schema but adds no new parameter-specific meaning, so 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 clearly states the tool checks up to 50 email addresses in one call and returns per-address verdicts plus a summary, using a specific verb ('Check') and resource. It distinguishes from sibling tools like validate_email by emphasizing the batch nature ('up to 50') and is unambiguous.

  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?

  It provides explicit usage context: split longer lists into chunks of 50, never run parallel calls because the API serialises jobs, and how to handle Unknown results (present separately, don't reject). However, it doesn't explicitly name alternative tools like validate_email for single addresses, so it's not a full 5.

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

• validate_emailA
  4.7/5.0
  Behavior5/5

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

  Adds significant behavioral context beyond the readOnlyHint and openWorldHint annotations: explains the meaning of 'Unknown' status, lists reasons (catch-all, greylisting, blocked SMTP), and warns never to treat Unknown as invalid. This is valuable operational guidance.

  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 serving a distinct purpose: action, statuses, clarification, and sibling alternative. No fluff or redundancy, and the most critical information is front-loaded.

  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?

  For a single-parameter tool with an output schema, the description covers the action, result interpretation, edge cases, and tool alternative. The 'Unknown' handling is especially important and fully addressed, leaving no significant gaps.

  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 already provides a description and example for the email parameter, with 100% coverage. The tool description adds minimal extra parameter info, so the baseline score of 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 clearly states the tool checks a single email address for deliverability, enumerating specific checks (syntax, MX, disposable-domain, SMTP probe). It also explicitly distinguishes from sibling validate_emails by noting the single-address scope, making the purpose unambiguous.

  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?

  Provides explicit guidance to use validate_emails when more than one address is present, which serves as an exclusion criterion. It also implies this tool is for single-address checks, and offers interpretive guidance on handling Unknown results, meeting the dimension fully.

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