Server Quality Checklist

Tool Scores

• create_dnsB
  3/5.0
  Behavior2/5

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

  With no annotations, the description must carry the safety and side-effect disclosure burden. It states the record-creation action and recommends dry-run, but doesn't explain whether existing records are replaced, whether special permissions/zone ownership are needed, how proxied/root/sensitive flags affect the write, or what response is returned. This is thin for a mutating DNS tool.

  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 short sentences, front-loaded with the core operation and closing with a safety preference. There is no filler, and the single most important execution hint ('Prefer dry_run first') is included.

  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 an 8-parameter mutating tool with no output schema and no annotations, this description is too sparse to be self-sufficient. It omits selection criteria versus upsert/update, effect of dry_run, handling of root/sensitive records, and return behavior, so the agent must infer or inspect the schema heavily.

  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 only 63%, leaving ttl, allow_root, and allow_sensitive undocumented in the schema, and the tool description does not fill those gaps. It repeats the record types already in the type enum and adds only the word 'one,' which is minor value beyond the input 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 opens with a concrete verb and object: 'Create one A, AAAA, CNAME, or TXT record.' This clearly identifies the operation and resource, and 'one' scopes it to a single record. It does not explicitly contrast with update_dns or upsert_dns, but the create verb is unambiguous enough for basic selection.

  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 only usage guidance is 'Prefer dry_run first,' which tells the agent to plan before writing but not when to choose create_dns over update_dns or upsert_dns. The intended context (new record creation) is implied by the name and phrase, but no explicit when/when-not or alternative routing is given.

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

• get_dnsA
  3.5/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It does disclose the 'allowlisted' constraint and implies a read-only operation via 'Get', but it does not explain what happens for non-allowlisted names, permission requirements, or response behavior. The description gives a basic picture but leaves meaningful gaps.

  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, direct sentence with no filler. It is appropriately sized for a simple get operation and front-loads the core action and scope.

  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?

  Given there is no output schema and no annotations, the description should provide more context. It omits the meaning of the 'type' parameter, the nature of the 'allowlisted' constraint, and what a successful response looks like. The description is not complete enough for reliable invocation without guessing.

  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 gives meaning to the 'name' parameter ('one allowlisted name'), but the 'type' parameter is entirely unexplained. This is insufficient for an agent to know what values are valid or how 'type' affects the request.

  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 a specific verb ('Get'), resource ('DNS records'), and scope ('one allowlisted name'). This differentiates it well from sibling tools like list_dns (which presumably returns all records) and the create/update/delete mutations.

  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 phrase 'one allowlisted name' implies this is for a single, specific name rather than listing all, but it does not explicitly state when to prefer this over list_dns or mention any alternatives. Usage context is implied rather than clearly specified.

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

• update_dnsA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description alone must disclose behavior. It usefully reveals that the tool operates on exactly one record and verifies after updating, which is beyond what the name implies. However, it does not disclose side effects, overwrite semantics, permissions, or failure behavior, leaving important operational traits unspecified.

  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 front-loads the action, resource, scope, and the verify-after behavior with no filler. Every phrase earns its place; the description is as short as it can be while still conveying the core operation.

  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 write tool with 8 parameters, no annotations, and no output schema, this description is under-specified. The agent is left without guidance on how the target record is identified, what dry_run/proxied/allow_root/allow_sensitive affect, or what a successful update returns.

  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?

  The description maps to the record types in the schema's enum but adds no meaning for ttl, allow_root, allow_sensitive, or the auto TTL choice. With parameter schema coverage at 63%, the uncovered flags remain unexplained by the description, so it does not materially compensate for the gaps.

  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 names a specific verb ('Update'), a specific resource ('A, AAAA, CNAME, or TXT record'), and a scoping constraint ('exactly one'), which clearly differentiates it from sibling tools like create_dns, upsert_dns, or delete_dns. It is immediately obvious what this tool does.

  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 phrase 'Update exactly one...' implies this is for modifying a single existing record, but the description never explicitly contrasts it with create_dns (new records), upsert_dns (create-or-update), or delete_dns (removal). Usage context is implied rather than clearly stated.

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

• upsert_dnsA
  3.5/5.0
  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, and it delivers meaningfully: 'idempotently' discloses repeat-call safety, 'create, update, or return NOOP' discloses the complete outcome set, and 'Prefer dry_run first' prescribes a safe workflow. It stops short of disclosing return behavior or side effects on existing records.

  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 totaling about 15 words, with the core behavior front-loaded in the first sentence and operational guidance in the second. Every word carries information; there is no filler or restatement of the tool name.

  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 captures the tool's essential contract — idempotent single-record upsert with a dry-run-first workflow — which is the context most likely to prevent mis-invocation. However, for an 8-parameter mutation tool with no annotations and no output schema, it leaves the agent uninformed about return values, the meaning of the allow_root/allow_sensitive gates, and the Cloudflare context implied by the proxied parameter.

  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?

  The description is entirely silent on all 8 parameters, and schema description coverage is only 63%. The three undocumented parameters — ttl, allow_root, and allow_sensitive — receive no explanation anywhere, leaving the security-relevant gate flags and the unusual ttl 'auto' option opaque to the agent. The description does nothing to compensate for this coverage gap.

  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 explains the non-obvious 'upsert' semantics explicitly: 'Idempotently create, update, or return NOOP for one DNS record.' It specifies the resource (DNS record), scope (one record), and the full outcome set. This inherently differentiates it from the create_dns and update_dns siblings, though it does not name them 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?

  'Prefer dry_run first' is a concrete, actionable usage directive that tells the agent to plan before writing. The idempotent create/update/NOOP semantics imply when this tool is preferable to create_dns or update_dns, but the description never explicitly states when to use this tool versus those alternatives or when not to use it.

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

• list_dnsA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of disclosing behavior. It does reveal that the tool lists records (a read operation) and that only 'allowlisted' records are included, which is a meaningful scoping detail. However, it omits information about pagination, result format, or what 'allowlisted' specifically entails, leaving some behavior unknown.

  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 that front-loads the core action and resource, then mentions the optional filters with no wasted words. Every word contributes useful information, making this a model of concise writing.

  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 list operation with two optional parameters and no output schema, the description covers the essential requirements: what it lists and the available filters. It could mention pagination or return format, but these are minor omissions given the low complexity and the clarity already provided.

  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 does by identifying 'name' and 'type' as optional filters, giving them a purpose beyond the bare schema. It does not specify allowed values, matching behavior, or format details, but for two simple parameters this partial explanation is adequate.

  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 resource ('allowlisted Cloudflare DNS records'), which clearly identifies the tool's function. It also notes optional filtering by type or name. However, it does not explicitly differentiate itself from siblings like get_dns, leaving the distinction between listing and retrieving to be inferred.

  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 a list of DNS records rather than a single record or performing mutations, but it offers no explicit guidance on when to choose this tool over get_dns or the other siblings. No exclusions or alternative conditions are stated, so the usage context is only implied.

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

• delete_dnsA
  3.9/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well by disclosing the destructive nature, requiring confirm_delete, and recommending dry_run as a safety step. It does not describe what dry_run actually does or the permanence of deletion, but the core behavioral safeguards are present.

  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 concise sentences with no filler. The core action is front-loaded and the safety requirements follow immediately. Every word earns its place.

  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 destructive tool with no annotations and no output schema, the description is incomplete. It omits the meaning of allow_root and allow_sensitive, the role of name and type, and what happens when dry_run is true or when no matching record exists. These gaps could lead an agent to misuse the tool.

  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 only adds meaning for confirm_delete and dry_run, while name, type, allow_root, and allow_sensitive remain unexplained. These are critical for correct invocation, especially the safety-related flags.

  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 ('Delete exactly one DNS record') with a clear resource and an explicit scope ('exactly one'). This distinguishes it from create, update, upsert, and list operations 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 Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear operational guidance: confirm_delete must be true and dry_run should be preferred first. It does not explicitly name alternative tools or conditions for using them, but the delete operation is naturally distinct from its siblings.

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