Server Quality Checklist

Tool Scores

• domain_searchB
  3/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint and openWorldHint, so the read-only nature is covered. The description adds that results are 'current people' and lists filter capabilities, but it does not disclose output format, pagination, or any behavioral side effects beyond what annotations already indicate.

  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 with no filler. Every word contributes value, and the core action plus filter list is front-loaded effectively.

  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?

  With 13 parameters, nested objects, zero schema description coverage, and no output schema, the description is far from sufficient for an agent to correctly invoke the tool. It provides only a high-level summary of filter types and does not cover numerous parameters or return expectations.

  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 names several filter categories (verification, location, job-title, decision-maker, aggregation, offset) that map to schema parameters, but it omits core inputs such as domain, company, limit, type, seniority, department, and required_field, leaving those without any added 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 ('Search') and resource ('Hunter v2 emails for one domain/company'), clearly indicating a domain-level email search tool. It distinguishes from person-level tools like email_finder, though it doesn't explicitly name any sibling to differentiate from.

  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 use this tool versus alternatives like email_finder or email_enrichment. It implies domain/company lookup but provides no exclusions, prerequisites, or comparison context, leaving tool selection to inference.

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

• discoverB
  3.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint and openWorldHint, so the safety profile is established. The description adds 'current' data and lists filter categories, but it does not disclose return behavior, pagination defaults, result limits, or matching semantics such as include/exclude/match behavior.

  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 a single front-loaded sentence with no filler. It gives the action and resource first, then lists filters compactly. It is appropriately sized for a summary, though it could add more value with a few targeted usage details.

  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?

  This is a high-complexity tool: 13 optional parameters, nested objects, no required parameters, no output schema, and zero parameter descriptions. The description only provides a high-level filter summary and leaves out essential operational context like how the query parameter interacts with structured filters, pagination, and what the response contains.

  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?

  With 0% schema description coverage, the description partially compensates by naming the main filter groups: organization, location, industry, headcount, type, year, keyword, technology, and funding. However, it omits parameter semantics for limit, offset, similar_to, and the include/exclude/match structures, so the compensation is incomplete.

  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 clearly states the action ('find companies') and the resource ('Hunter Discover v2'), and it enumerates the main filter dimensions. It does not explicitly differentiate from sibling tools like company_enrichment or domain_search, but the 'find companies' framing and filter list make the core purpose reasonably distinct.

  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?

  No guidance is given about when to use Discover compared with sibling tools such as company_enrichment, domain_search, or email_finder. The description implies broad company discovery use, but it does not state exclusions, prerequisites, or alternative routing.

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

• list_leadsB
  3.1/5.0
  Behavior3/5

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

  The readOnlyHint and openWorldHint annotations already communicate that this is a safe, non-exhaustive read operation. The description adds little behavioral detail beyond naming the filter categories, so it neither enriches nor contradicts the annotation-provided behavior.

  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 a single, front-loaded sentence with no filler. The long enumeration of filter categories is somewhat unwieldy, but it is compact and avoids repetition.

  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 the tool's complexity—37 parameters, nested location and date objects, and no output schema—the description is too thin. It does not mention pagination defaults, result shape, how filters combine, or important parameters like limit; an agent is left guessing on several operational details.

  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?

  With only 8% schema description coverage and 37 parameters, the description must compensate heavily. It provides a high-level grouping of filter types (identity, company, status, verification, etc.) but does not explain individual parameter meanings, accepted value formats, or the relationship between categories and specific parameter names, leaving the agent to infer mappings.

  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 (Hunter leads), and enumerates the filter dimensions, so an agent can tell this is a lead-list retrieval tool. It does not explicitly contrast with sibling tools, but the resource and operation are distinct enough among the listed siblings.

  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 leads with various filters, which gives basic usage context. It does not explicitly state when to prefer this over siblings like domain_search or email_finder, and it offers no exclusion criteria.

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

• email_finderB
  3.4/5.0
  Behavior4/5

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

  Beyond the readOnlyHint and openWorldHint annotations, the description discloses that the tool not only finds an email but also automatically verifies it, and that the result is a 'most likely' match. This adds meaningful behavioral context about heuristic searching and verification that annotations alone do not convey.

  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 entire description is one compact, front-loaded sentence with no filler. It states the action, the resource, and the primary input modes in an efficient way.

  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?

  With 7 optional-looking parameters, no required fields, no output schema, and no schema descriptions, the description leaves critical gaps: valid parameter combinations, required inputs, return format, and verification failure behavior. The tool's behavior is not fully specified for an agent to call it confidently.

  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%, but the description only loosely maps the domain/company/name parameters and the LinkedIn handle. It does not clarify the relationship between domain and company, whether full_name vs first_name/last_name matters, or what max_duration controls. The description only partially compensates for the missing schema descriptions.

  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 clearly identifies a specific action ('Find and automatically verify') and a specific resource ('professional email'), and names the two main input paths. It inherently distinguishes itself from email_verifier, since it finds rather than merely verifies, though it does not explicitly name 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?

  It communicates the intended input combinations: company/domain plus name, or LinkedIn handle. However, it provides no guidance on when to prefer this tool over siblings like email_enrichment, domain_search, or email_verifier, and no exclusions or preconditions are stated.

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

• create_leadA
  3.9/5.0
  Behavior4/5

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

  The annotations already signal a write operation (readOnlyHint=false), and the description adds the useful behavioral trait that this is a 'single-attempt mutation,' implying no automatic retry. It does not detail error handling, authentication needs, or side effects, but given the annotation coverage this is meaningful added 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?

  Two short sentences with no filler; the primary action and required input are front-loaded, and the 'single-attempt mutation' caveat earns its place as an important behavioral signal.

  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 19-parameter mutation with no output schema, this description is incomplete. It does not describe the return value, error behavior, duplicate handling, or how list placement fields interact, so an agent cannot fully anticipate the outcome of invoking it.

  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?

  With zero schema description coverage and 19 parameters, the description carries the burden of explaining fields, but only groups them into vague categories like 'current lead fields' and 'list placement.' It does not explain individual parameters, relationships such as leads_list_id vs leads_list_ids, or custom_attributes structure.

  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 and resource: 'Create one Hunter lead' from an email plus optional fields. This clearly distinguishes it from the sibling read/enrichment tools like list_leads and email_finder, which are not mutations.

  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 states that the tool is for creating a lead and identifies the required input (email) and optional categories, giving clear context for when to call it. It does not explicitly list exclusions or alternative tools, but no sibling tool performs lead creation, so the intended use is clear.

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

• email_enrichmentA
  3.9/5.0
  Behavior3/5

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

  Annotations already signal readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful context by naming Hunter v2 as the backend and noting the Clearbit-compatible output option, but it does not describe response shape, failure modes, or what happens when neither input is provided.

  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 with no filler. The core action, inputs, provider, and optional output format are all front-loaded, and every clause earns its place.

  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 is minimally adequate for a simple enrichment lookup, but important context is missing: there are no required parameters in the schema, yet the description implies at least one of email or linkedin_handle is needed. There is also no output schema, and the description does not indicate the shape of the returned enrichment data or how errors should be handled.

  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 only 33%, but the description compensates by explaining the roles of email and linkedin_handle ('from an email address or LinkedIn handle') and clearbit_format ('optionally in Clearbit-compatible format'). It does not specify the expected LinkedIn handle format or whether email and linkedin_handle are mutually exclusive, but it provides more meaning than the raw schema 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 names a specific verb ('Enrich'), a specific resource ('a person'), and the input sources ('email address or LinkedIn handle'), while also identifying the provider ('Hunter v2'). This clearly distinguishes it from sibling tools like email_finder, email_verifier, and company_enrichment based on the operation and resource.

  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 should be used when you have an email address or LinkedIn handle and need person enrichment, but it does not explicitly state when to prefer this over siblings such as combined_enrichment or company_enrichment. No alternatives or exclusions are mentioned, so the agent must infer routing from the wording alone.

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

• company_enrichmentA
  4/5.0
  Behavior3/5

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

  The annotations already declare readOnlyHint=true and openWorldHint=true, so the read-only safety profile is covered. The description adds useful context about the underlying provider and the Clearbit-compatible format option, but it does not describe rate limits, returned fields, or failure behavior. This is acceptable but not exceptional given 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 a single sentence with no filler. It front-loads the action and resource, then adds the two most decision-relevant modifiers: the provider and the optional output format. Every part 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 simple, read-only, two-parameter tool, the description covers the required input, the optional flag, and the data source. There is no output schema, and the description does not enumerate return fields, but 'enrich a company' reasonably implies the returned payload. The annotation already covers safety, so the definition is complete enough for correct invocation.

  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 only 50%, with the domain parameter undocumented in the schema. The description helps by implying that domain is the company's domain and that clearbit_format controls the output shape, but it does not specify domain syntax or what the native Hunter format looks like. It partially compensates for the schema gap without fully closing it.

  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 starts with a specific verb, 'Enrich', and clearly identifies the resource as 'a company' and the input source as 'its domain'. It also names the provider (Hunter v2) and an optional output format (Clearbit-compatible), which helps distinguish it from sibling tools like email_enrichment or combined_enrichment.

  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 phrase 'from its domain' gives a clear triggering condition: use this tool when you have a company domain and need company enrichment data. However, it does not explicitly mention when not to use it or point to an alternative such as combined_enrichment, so it stops short of full routing guidance.

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

• account_infoA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true, so the safe read-only nature is covered. The description adds useful specificity about what exactly is read—account plan and unified/per-type credit balances—but does not describe response format, potential staleness, or access requirements.

  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 that wastes no words. It leads with the action, names the resource, and includes the most decision-relevant detail in a compact phrase.

  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?

  This is a simple, zero-parameter read operation. The description covers the account plan and the full credit-usage picture, including unified and per-type balances, which is sufficient context for an agent to invoke the tool and interpret its result.

  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 an empty input schema, so there is no parameter documentation burden for the description to carry. Baseline 4 is appropriate because nothing is missing and no parameter-level explanation could add value.

  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 ('Read'), a precise resource ('Hunter v2 account plan'), and the exact data returned ('current credit usage', 'remaining unified or per-type balances'). This clearly distinguishes it from all sibling tools, which are about leads, searches, enrichment, and verification.

  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 when to use the tool: whenever account-level credit or plan information is needed. However, it does not explicitly state when not to use alternatives or mention any related tools, though the sibling set makes such confusion unlikely.

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

• combined_enrichmentA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds useful behavioral context beyond annotations and schema by naming the external source ('Hunter v2') and the optional output shape ('Clearbit-compatible format'). It does not mention rate limits or exact response shape, but with annotations carrying the heavy safety burden, this is sufficient.

  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 dense sentence that packs the action, target, input, source, and optional format with no wasted words. The core action is front-loaded, making the tool's purpose immediately scannable.

  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 two-parameter tool with read-only and open-world annotations, the description covers the essential call semantics: email input, combined enrichment scope, the Hunter v2 provider, and the optional Clearbit-compatible format. The lack of an output schema means the exact return shape is not described, but the operation is simple enough that this is a minor gap.

  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 documents email with format constraints and clearbit_format with a description, covering 50% of parameter semantics. The description reinforces that the email drives the combined person+company enrichment and that output can be Clearbit-shaped, but it does not add new syntax or constraints beyond what the schema gives. This is adequate but not comprehensive.

  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 ('Enrich'), the resource ('both a person and their company'), and the input ('from one email'), so an agent can immediately understand what this tool does. This clearly differentiates it from sibling tools like email_enrichment and company_enrichment, which cover only one side.

  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 phrase 'both a person and their company' clearly implies the use case: choose this tool when both person and company enrichment are needed from a single email. It does not explicitly state when to prefer the sibling tools, so it stops short of a full when/when-not rule, but the context is not ambiguous.

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

• email_countA
  4.2/5.0
  Behavior4/5

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

  With readOnlyHint=true already covering safety, the description adds valuable behavioral context: the tool returns no addresses and can filter by address type. It also clarifies that the query target is a domain or company. No contradiction with annotations exists.

  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, front-loaded sentence that conveys purpose, scope, optional filtering, and a critical behavioral constraint without redundant 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?

  For a simple count tool with read-only annotations and no output schema, the description sufficiently covers the invocation intent. The only minor gap is the absence of any statement about required parameters or expected return format.

  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 explain parameters. It covers 'domain'/'company' as the target and 'type' as an optional personal/generic filter, but it does not state that exactly one of domain or company is likely required, nor clarify the relationship between the two parameters.

  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 opens with a specific verb ('Count'), names the resource ('Hunter email coverage'), specifies the scope ('domain/company'), and explicitly states the output exclusion ('without returning addresses'). This clearly distinguishes it from address-returning siblings like email_finder and email_verifier.

  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 conveys a clear use case: obtain counts of email coverage, optionally filtered by personal or generic addresses. The phrase 'without returning addresses' implicitly warns against using this tool when actual addresses are needed, though it does not name a specific alternative tool.

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

• email_verifierA
  4.3/5.0
  Behavior4/5

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

  The annotations already communicate read-only behavior and an open-world result. The description adds value by disclosing the Hunter v2 backend and enumerating the exact evidence types returned, so the agent knows what kind of output to expect. No contradiction with the readOnlyHint.

  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 entire purpose and output contract are conveyed in a single front-loaded sentence with no filler. Every clause adds useful information for invoking the tool.

  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 simple single-parameter, read-only verification tool with no output schema, the description is complete: it states the input, the API, and the full list of verification dimensions returned. Nothing essential is missing for correct selection or invocation.

  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?

  With only one required parameter and no description in the schema, the description's 'one email address' maps cleanly to the email parameter. However, it adds no additional semantics beyond the schema's format/pattern constraints; the schema is left to carry most of the parameter documentation burden.

  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 ('Verify'), a precise resource ('one email address'), and names the exact API version and result fields (deliverability, score, SMTP/MX, accept-all, webmail, disposable, source evidence). This clearly separates it from sibling tools like email_finder, which find addresses rather than verify a known one.

  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 establishes clear context: use this when you already have a single email address and need verification results. It does not explicitly enumerate when-not-to-use or name email_finder as an alternative, but the single-address scope makes the intended invocation obvious.

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