send16-mcp

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

With no annotations, the description must disclose all behavioral traits. It indicates that activation causes enrollment to start, but does not mention idempotency, side effects, required permissions, or whether activation can be undone. Only a minimal behavioral effect is described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, no redundant words. The first sentence provides the action, the second clarifies the consequence. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one required parameter, no output schema), the description adequately covers the core behavior. However, it does not indicate what the response looks like upon success or error, which would improve completeness.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds no additional meaning beyond the schema; it does not explain how to obtain the automationId or the role of apiKey. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (activate) and the resource (automation), and explains the effect: 'New events matching its triggers will start enrolling contacts.' This distinguishes it from siblings like pause_automation and enroll_in_automation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage (to start enrollment), but lacks explicit guidance on when to use vs alternatives, prerequisites, or when not to use. For example, it does not state that the automation must be in a paused or inactive state prior to activation.

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

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

No annotations are provided, and the description does not disclose any behavioral traits such as idempotency, handling of duplicate contacts, or whether adding to a non-existent audience fails. The description only states the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, efficient sentence that conveys the core functionality without unnecessary words. It is appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and lack of output schema, the description is minimally adequate. However, it omits details like error cases (e.g., invalid audience ID) and behavior when contacts already in the audience.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond the schema's parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add'), the resource ('contacts to an audience'), and the method ('by ID'). It is unambiguous and distinguishes the tool from its sibling 'remove_contact_from_audience'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no context about the meaning of adding contacts to an audience.

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

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

No annotations are provided, so the description carries the full burden. It discloses that notes are private to workspace members, but omits other behavioral traits such as whether adding a note triggers notifications, permissions required (beyond workspace membership), or the tool's behavior on nonexistent conversations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that conveys the essential information without any wasted words. Every part is meaningful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool, the description covers the core purpose and a key caveat. However, it lacks details on return value (no output schema), potential side effects, or constraints like note length limits, which would improve completeness.

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

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

Schema description coverage is 100%, so the baseline is 3. The tool description does not add meaning beyond what the schema already provides for parameters. It confirms the overall purpose but offers no new parameter-specific context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add'), the resource ('private internal note on a conversation'), and a key property ('visible only to workspace members'). This effectively distinguishes it from sibling tools like 'update_convo' or 'send_reply'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies when to use (adding a private note) but does not explicitly specify when not to use or mention alternative tools. It provides no exclusion criteria or contextual hints for choosing between tools.

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

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

No annotations are provided, so the description carries full burden. It discloses that DNS records are returned and that verification is needed, but does not mention potential issues like idempotency, rate limits, or handling of existing domains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences that are efficient and front-loaded, containing no unnecessary words. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description explains the return value (DNS records). The tool has only 2 simple parameters, and the description provides enough context for an agent to use it correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the schema's parameter descriptions for apiKey and domain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Register' and resource 'sending domain', clearly distinguishing it from sibling tools like check_domain_health and list_domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description explains what the tool does and instructs the user to call check_domain_health afterward, providing clear context. However, it does not explicitly state when not to use this tool or mention alternatives.

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

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

With no annotations, the description must convey behavioral traits. It states the main effect (blocking future sends), which is useful, but omits details like reversibility, idempotency, or error handling. The transparency is adequate but not thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two concise sentences that immediately convey the tool's purpose and effect. No redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no output schema, and low schema coverage, the description is insufficient. It lacks details on authentication requirements, parameter formats, or expected outcomes, leaving the agent without essential context for correct usage.

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

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

Schema description coverage is only 25%. The description does not explain the meaning or usage of 'notes', 'apiKey', or 'reason' beyond their schema definitions. For example, 'reason' has an enum but no context on when to use each value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('add'), the resource ('email to the suppression list'), and the consequence ('future sends will be blocked'). It distinctively separates this from sibling tools like 'remove_suppression' and 'list_suppressions'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance is provided on when to use this tool versus alternatives. For example, it does not mention scenarios like adding emails due to bounces, complaints, or manual actions, nor does it explain when not to use it or potential prerequisites.

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

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

No annotations are provided, so the description carries full burden. It mentions 'triggers a fresh DNS lookup' but does not disclose whether the operation is read-only, authentication requirements, rate limits, or error behavior. Lack of safety or idempotency information limits transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences with no redundant words. First sentence defines purpose and scope; second adds a key behavioral trait. Every sentence adds value, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's core function and records checked but omits output format or return value. No error handling or response schema is described. Given the tool's simplicity and lack of output schema, it is partially complete but could be improved by specifying what the response contains.

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

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

Schema description coverage is 100% (both 'apiKey' and 'domainId' have descriptions). The description adds no extra parameter-level meaning beyond the schema, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'check' and the resource 'DNS health of a specific domain', listing specific records (DKIM, SPF, DMARC, MX). It distinguishes this tool from siblings like 'add_domain' or 'list_domains' by focusing on health verification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage (e.g., after adding a domain) but does not explicitly state when to use this tool versus alternatives or provide any exclusion criteria. Sibling tools like 'get_deliverability_status' or 'add_domain' are not mentioned, leaving the agent to infer context.

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

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

With no annotations, the description carries full burden. It states that each matching event sends one email, but does not disclose idempotency, overwrite behavior, rate limits, or authentication nuances beyond the apiKey parameter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, front-loaded with core purpose, zero unnecessary words. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Missing output schema and annotations; description does not explain return value, error states, or pagination. For a tool with 7 parameters (3 required), this is insufficient.

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

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

Schema description coverage is 86%, high enough that baseline is 3. The description adds the behavioral context of sending one email, but does not elaborate on parameter meanings beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Create', the resource 'Action', and the specific function: mapping an event name to a transactional template that sends one email per event. This distinguishes it from siblings like send_email or send_broadcast which directly send messages.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No explicit guidance on when to use this tool versus alternatives like send_event or update_action. Lacks context on prerequisites or scenarios where this is appropriate.

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

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

With no annotations, the description bears the full burden of disclosure. It only states 'Create,' implying a mutation, but does not clarify required permissions, side effects, or return behavior. This is insufficient for a creation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

While the single sentence is short, it is under-specified; conciseness should be paired with completeness. The description does not earn its place as it adds negligible value beyond the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with three parameters, no output schema, and no annotations, the description is critically incomplete. It lacks definition of what an audience is, parameter constraints, success behavior, and any contextual information needed for an agent to use it correctly.

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

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

The description adds no meaning to the parameters. Schema coverage is only 33% (only apiKey has a description), and the tool description does not mention or explain any parameters, leaving agents uninformed about mandatory fields like 'name' or optional ones like 'description'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Create a new audience.' is essentially a tautology, restating the tool name. While it indicates the verb and resource, it adds no new information beyond the name itself, failing to provide specific context or differentiate from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance is provided on when to use this tool versus alternatives like 'delete_audience' or 'list_audiences'. The description lacks any context about appropriate usage scenarios or prerequisites.

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

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

The description discloses that the campaign is created in draft status, a key behavioral trait, but does not mention what the tool returns, error handling, or authentication requirements. With no annotations, more transparency would be beneficial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

A single sentence that is concise and front-loaded with the core purpose. No redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the essential purpose and draft status but lacks information about return values, error scenarios, and prerequisites. Given 7 parameters and no output schema, it is adequate but not complete.

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

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

The description adds no parameter-specific information beyond the schema, which has 100% coverage. Per guidelines, baseline 3 applies when schema coverage is high and description adds no extra context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a new email campaign in Send16, specifying the verb 'create' and the resource 'email campaign'. It also mentions the draft status, which distinguishes it from sending or updating campaigns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage when creating a campaign and notes it can be edited before sending, but it does not explicitly state when not to use this tool or provide alternatives. Sibling tools like update_campaign and send_campaign are not referenced.

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

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

With no annotations, the description must disclose behavioral traits. It mentions auto-subscription but omits critical details: handling of duplicate emails, confirmation emails, rate limits, or success/failure behavior. The agent lacks sufficient behavioral context to use this tool safely.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, no redundant information, front-loaded with the core action. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with 6 parameters (including nested objects) and no output schema or annotations, the description is too sparse. It fails to explain return value, error cases, or duplicate contact behavior, leaving the agent under-informed.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds no parameter-specific information beyond what the schema already provides, but does not detract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (Add a new contact) and the resource (Send16 audience), and distinguishes from siblings like update_contact and delete_contact by specifying 'Add a new contact' and noting auto-subscription.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implicitly suggests use for adding new contacts, but provides no explicit guidance on when to use this tool versus alternatives like import_contacts or add_contacts_to_audience, nor any when-not-to-use conditions.

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

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

With no annotations provided, the description must bear the full burden of behavioral disclosure. It mentions opt-in behavior but omits important traits such as required permissions, potential side effects, or rate limits. The mutation nature is implicit but not elaborated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is concise at two sentences, front-loading the primary action. While efficient, it could afford a bit more detail without becoming verbose, making it slightly under-informative for its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 parameters, no output schema, and no annotations, the description should explain the creation process, return value (e.g., created topic ID), and any prerequisites. It fails to address these, leaving gaps for an AI agent.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides for each parameter. It does not clarify nuances like auto-derivation of slug or the effect of isDefault.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Create' and the resource 'a new subscription topic', distinguishing it from siblings like update_topic, delete_topic, and list_topics. It also adds context about opt-in via the preference center.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description hints at usage context (opt-in mechanism) but provides no explicit guidance on when to use this tool vs. alternatives like update_topic or delete_topic. No when-not-to-use or alternative recommendations are given.

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

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

With no annotations, the description carries the burden. It discloses that events are sent as POSTs with HMAC-SHA256 signature. But it omits details like whether registration is immediate, validation steps, or what happens on failure. Moderate transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, no filler. The purpose is front-loaded. Minor typo ('Send16') detracts slightly but overall concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with 5 parameters, no output schema, and no annotations, the description is somewhat complete but lacks details on response, permissions, or error behavior. The plan feature mention adds context.

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

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

Schema coverage is 100%, so baseline is 3. The description adds that the URL is an endpoint receiving events with signature, but this only slightly reinforces schema descriptions. No additional meaning for other parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Register') and resource ('outgoing webhook endpoint'), distinguishing it from sibling tools like list_webhooks or delete_webhook. The mention of 'Send16' is a minor typo but does not obscure the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description mentions 'Outgoing webhooks are a plan feature', which provides a constraint on usage. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., regenerate_webhook_secret) 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.

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

With no annotations, the description bears full responsibility for behavioral transparency. It merely states 'delete' without disclosing whether the operation is irreversible, has cascading effects, or requires specific permissions, which is insufficient for safe use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is extremely concise (one sentence), but it sacrifices useful detail. While not verbose, its brevity without additional context makes it minimally adequate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a delete operation with two parameters (one optional), the description lacks context about return values, side effects, error conditions, or behavior if the action does not exist. It feels incomplete for an AI agent to use safely.

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

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

Schema descriptions already cover both parameters (apiKey and actionId) with 100% coverage. The description adds no extra meaning beyond what the schema provides, earning a baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Delete an Action' clearly states the verb and resource, making the tool's purpose easy to understand. However, it does not differentiate from sibling tools like create_action or get_action, which is acceptable for a distinct action like deletion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites, such as the action existing before deletion. It lacks any contextual usage advice.

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

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

With no annotations, description carries full burden. It discloses that contacts are preserved while list memberships are removed, providing key behavioral insight beyond the name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence conveys purpose, resource, and critical behavior with no wasted words. Front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple delete tool with full schema coverage, description is mostly sufficient. Missing note on return value, but acceptable given lack of output schema.

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

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

Schema coverage is 100%, so description adds no extra meaning to parameters. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verb 'Delete' and resource 'audience (list)', and clarifies that contacts are not deleted, distinguishing it from contact deletion tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Description states the operation but does not provide guidance on when to use this tool versus alternatives like remove_contact_from_audience or delete_contact. Usage context is implied rather than explicit.

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

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

Discloses the critical behavioral constraint that only draft campaigns can be deleted, while sent campaigns cannot. With no annotations provided, the description carries full burden and adequately conveys this limitation, though it could mention that deletion is irreversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences with zero waste. Front-loaded with the core action and constraint, every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 2-parameter tool with no output schema, the description is largely complete. It covers the essential constraint about draft vs. sent. Missing guidance on what happens upon attempting deletion of a sent campaign (e.g., error response), but otherwise adequate.

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

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

Schema description coverage is 100% for the two parameters, so baseline is 3. The description adds no extra meaning beyond the schema; the parameter 'campaignId' is simply implied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool deletes draft campaigns, distinguishing that sent campaigns cannot be deleted (only archived). The verb 'delete' and resource 'draft campaign' are specific, and the distinction from archiving differentiates from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Explicitly provides when to use (draft campaigns) and when not to use (sent campaigns), and mentions the alternative action (archive). This gives clear guidance for the agent.

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

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

Discloses irreversibility and deletion of associated events, but lacks details on permissions, rate limits, or cascade effects. Without annotations, more depth would be beneficial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two short sentences, no fluff. Efficient but 'Irreversible.' as a standalone sentence is slightly fragmented.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a simple delete tool: defines purpose and finality. Lacks mention of return behavior or undo possibilities, which would improve completeness.

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

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

Schema covers both parameters (100% coverage). Description adds no extra meaning; baseline applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb 'Delete' and resource 'contact' with added detail 'all associated events.' Distinguishes from siblings like 'remove_contact_from_audience' but could specify scope more precisely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Only hints at caution via 'Irreversible.' No explicit when-to-use vs alternatives, no prerequisite or context guidance.

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

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

Explicitly states that all subscribers will be detached, which is a behavioral consequence not captured in the input schema. With no annotations provided, this disclosure is valuable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two concise, informative sentences with no superfluous words. Each sentence adds value: the first states the action, the second highlights a key side effect.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple delete operation, the description covers the primary effect. It could optionally mention idempotency or error handling for missing topics, but overall it is sufficiently complete.

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

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

The input schema already provides 100% coverage with descriptions for both parameters. The description does not add any additional semantic meaning beyond what the schema offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool deletes a subscription topic and adds the side effect of detaching subscribers. This distinguishes it from sibling tools like create_topic, update_topic, and list_topics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives. For example, it does not suggest using list_topics first to confirm the topic exists, or mention scenarios where deletion is inappropriate.

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

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

The description only states 'Delete' which implies a destructive action, but it does not disclose whether the deletion is reversible, if there are any side effects (e.g., breaking integrations), or authorization requirements. With no annotations, the agent lacks critical behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is very concise—only four words—which avoids verbosity. However, it lacks any structure or additional details that could aid the agent, but for a simple operation, brevity is acceptable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a straightforward delete operation, the description provides minimal context. It does not explain the return value (since no output schema) or potential errors, but given the tool's simplicity, it is just adequate.

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

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

The input schema has 100% description coverage for both parameters (apiKey and webhookId), so the description adds no further meaning. The baseline score of 3 is appropriate as the schema already documents parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Delete an outgoing webhook endpoint' clearly specifies the action (delete) and resource (outgoing webhook endpoint). It distinguishes itself from sibling tools like create_webhook and list_webhooks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides no guidance on when to use this tool versus alternatives, such as when a webhook should be removed or prerequisites like needing the webhook ID. It is implied but not explicit.

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

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

No annotations are provided, so the description carries the burden. It states 'Use AI to generate,' which implies a generative (non-read-only) operation that likely consumes API credits. It does not disclose side effects, rate limits, or authentication requirements beyond the apiKey parameter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is two sentences, both providing valuable information: the action (generate using AI) and the output (ready-to-use HTML). It is concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (6 parameters, no output schema), the description mentions the return type (HTML) but lacks details on the AI model, potential costs, or API key usage. It is adequate but incomplete.

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

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

Schema coverage is 100% with parameter descriptions. The tool description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it generates a complete email HTML template from a description, distinguishing it from sibling tools like 'render_email_content' which likely renders existing content. However, it could more explicitly differentiate from 'generate_email_from_url'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage when a user needs to create an HTML template from a description, but it does not specify when not to use it or mention alternative tools for similar tasks like 'render_email_content' or 'send_email'.

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

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

No annotations are provided, so the description must disclose behavioral traits. It does not mention side effects, required permissions, whether the duplicate is a full copy, or what happens to the original campaign. The phrase 'as a new draft' is helpful but insufficient detail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is two sentences with no extraneous words. The primary action is front-loaded, and the use cases follow logically. Perfectly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema and no annotations, the description should explain expected return value (e.g., the new campaign ID), any constraints (e.g., campaign status requirements), and what is duplicated. It lacks these details, leaving the agent with gaps.

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

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

Schema coverage is 100%, so the schema already documents both parameters. The description adds no additional meaning beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('duplicate a campaign') and the outcome ('as a new draft'). It distinguishes from siblings like 'create_campaign' and 'update_campaign' by specifying duplication. The use cases ('A/B variants or re-using a successful template') reinforce the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides clear contexts for using the tool (A/B testing, template reuse). It does not explicitly list when not to use it or mention alternatives, but the intended usage is unambiguous.

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

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

Without annotations, the description carries full burden. It discloses the precondition (active automation) but does not mention effects like idempotency, error behavior, or success response. This is adequate but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two focused sentences. No wasted words. Front-loaded with purpose, then constraint and alternative. Excellent conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 3-parameter tool with no output schema, the description covers purpose, precondition, and alternative. Could mention expected result (e.g., enrollment confirmation) but overall complete enough.

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

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

Schema coverage is 100% and parameter descriptions in schema are complete. The description adds no new parameter semantics beyond restating the action's purpose. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Manually enroll a contact in an active automation.' It specifies the resource (contact) and the target (automation), and distinguishes from siblings like 'send_event' and 'activate_automation'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Explicit usage constraints: 'The automation must be in active status' and an alternative: 'Use send_event for event-driven enrollment.' This provides clear when-to-use and 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.

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

No annotations are provided, so the description must carry full behavioral disclosure. It states the tool scrapes a URL and generates an email draft, but omits important details such as required permissions, error handling (invalid URL), rate limits, or privacy considerations. The return format is mentioned, but behavioral traits beyond that are lacking.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, well-structured sentence that fully conveys the tool's purpose and output. No redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema, the description usefully explains the return values (subject, preview text, HTML body). It does not cover edge cases or prerequisites (e.g., URL accessibility), but for a scraping-and-generation tool, it provides sufficient completeness.

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

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

Schema description coverage is 100%, with each parameter having a clear description in the schema. The tool description adds no further parameter-specific meaning beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the verb 'scrape' and resource 'URL', states the output (subject, preview text, HTML body), and gives usage examples like 'launch blog post or product page', which effectively distinguishes it from sibling tools like design_email_template or send_email.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides clear context with examples of when to use the tool (blog post, product page). However, it does not explicitly state when not to use it or mention alternatives among siblings.

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

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

No annotations are provided, and the description does not disclose behavioral traits such as read-only nature, authentication needs, rate limits, or side effects. For a 'get' operation, stating it is safe or read-only would add value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, concise sentence that is front-loaded with the core purpose. It contains no unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of an output schema and the simplicity of the tool (2 parameters, no nested objects), the description is adequate but minimal. It does not explain the return format or what fields an 'Action' contains, which could be helpful for an agent.

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

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

Schema description coverage is 100%, so the schema already documents both parameters sufficiently. The description adds no additional meaning beyond 'Get a single Action...', which is minimal but acceptable given the high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the resource 'Action' and specifies what is included ('trigger config and template binding'), effectively distinguishing it from sibling tools like list_actions, create_action, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage for retrieving a single action's details, but it does not explicitly state when to use this tool versus alternatives like list_actions or get_automation, nor does it provide exclusions or prerequisites.

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

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

Covers basic read behavior and returned fields but omits idempotency, error conditions, and auth requirements (apiKey parameter not mentioned). No annotations to supplement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence, 12 words, no redundancy. Front-loaded with purpose and key details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return shape is partially described (trigger, steps, status), compensating for missing output schema. No output schema, but description gives enough context for a simple retrieval.

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

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

Schema coverage is 100% so baseline is 3. Description adds no extra meaning beyond the schema's parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool retrieves a single automation by ID, specifying included attributes (trigger, steps, status). Distinct from sibling list_automations and activate_automation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No explicit guidance on when to use this tool versus siblings like list_automations or get_automation_stats. Usage is implied but not stated.

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

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

No annotations exist. Description discloses return type (aggregate analytics) and specific metrics, but does not mention side effects, permissions needed, or behavior beyond listing. Partial transparency, but not comprehensive for a no-annotation case.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single, focused sentence that directly states purpose and key metrics. No wasted words. Front-loaded with action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so description must clarify return structure. It names metrics but not their format (e.g., nested steps, totals vs rates). Among many sibling tools, differentiation is minimal. Adequate but incomplete.

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

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

Schema covers both parameters (apiKey, automationId) with 100% description coverage. Description does not add new semantic insights beyond what the schema provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb 'Get' + resource 'aggregate analytics for an automation', listing exact metrics (enrollments, completed, exited, open/click rates per step). Clearly distinguishes from siblings like get_automation (which returns automation details) and get_campaign_stats (campaign-specific).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives like get_automation or list_automations. No prerequisites, when-not-to-use, or context provided. Agent must infer from name alone.

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

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

No annotations are provided, so the description must cover behavioral aspects. It states what the tool retrieves (color, logo, fonts, DESIGN.md) but does not disclose if it is read-only, authentication requirements beyond the apiKey parameter, or any side effects. The description is adequate but lacks detail on permissions or request impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, well-structured sentence that front-loads the key action and includes specific details about what is returned. Every word is essential, no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description provides useful context by listing the brand settings (colors, logo, fonts, DESIGN.md). However, it could mention the response format or any pagination/limits. Overall, it is sufficiently complete for a simple get operation.

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

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

The only parameter 'apiKey' is fully described in the schema (100% coverage). The tool description does not add additional meaning beyond the schema, so it scores the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as retrieving the workspace's brand settings, listing specific elements (colors, logo, fonts, DESIGN.md). It uses a strong verb 'Get' and a specific resource, distinguishing it from sibling 'update_brand'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage for obtaining brand settings but does not provide explicit guidance on when to use this tool versus others, nor does it mention when not to use it. No alternatives are listed.

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

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

No annotations are provided. The description lists the metrics returned, giving a clear idea of the output, but does not disclose any behavioral aspects like required permissions, rate limits, or whether the operation is read-only (though implied).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence that is concise and front-loaded, containing no unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema, the description compensates by listing the key metrics returned (open rate, click rate, bounce rate, delivery metrics). However, it lacks details on response format or pagination. Given the tool's simplicity, it is mostly complete.

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

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

Schema description coverage is 100% (apiKey and campaignId are documented in the schema). The description does not add additional meaning beyond what the schema already provides, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action (Get) and resource (campaign statistics), listing specific metrics (open rate, click rate, bounce rate, delivery metrics). This distinguishes it from sibling tools like get_automation_stats or list_campaigns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives (e.g., get_automation_stats for automation stats, list_campaigns for campaign overview). No prerequisites or contextual clues provided.

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

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

Without annotations, description provides minimal behavioral info. It mentions basis (opens, clicks, replies) but doesn't disclose if the tool is read-only, permission requirements, or response structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence, 12 words, directly states purpose. No extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only query with no output schema, the description doesn't specify the response format beyond the score range. It could mention example return structure or error conditions.

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

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

Schema covers both parameters with descriptions. The description adds no additional parameter-level context beyond what schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool returns a numeric health score (0-100) based on recent engagement metrics, distinguishing it from siblings like get_contact_timeline or search_contacts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives. For example, it doesn't mention that for detailed engagement breakdown, one should use get_contact_timeline.

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

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

No annotations provided; description does not disclose behavior such as pagination limits, rate limits, auth requirements, or whether it is read-only. Minimal behavioral insight.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence is efficient and front-loaded with purpose. No redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema; description omits details on pagination, ordering, time range, or return format. Incomplete for a list-retrieval tool.

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

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

Schema coverage is 100% with descriptions for all parameters. Description adds no extra semantics beyond schema, meeting baseline but not exceeding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description specifies verb 'Get' and resource 'contact activity timeline' with concrete examples. Clear what tool does, though does not explicitly differentiate from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives like list_contacts or get_contact_health_score. Lacks context for selection.

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

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

No annotations are provided, so the description carries the full burden. It states the tool retrieves a conversation with posts, which is clear, but it omits details like authentication requirements, rate limits, or error behavior. Adequate but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single concise sentence (12 words) that front-loads the core purpose. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers what the tool returns (a conversation with its thread), but could mention if pagination or sorting applies. Still, for a simple get-by-ID tool, it is sufficiently complete.

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

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

Schema coverage is 100% with descriptions for both parameters ('id' and 'apiKey'). The tool description adds no additional meaning beyond what the schema already provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the verb 'Get', the resource 'a single conversation', and the scope 'with its full thread of posts (incoming + outgoing)'. This clearly distinguishes it from sibling tools like list_convos which would return multiple conversations without thread details.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance is provided on when to use this tool versus alternatives such as list_convos, get_message, or update_convo. There is no mention of prerequisites or use case context.

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

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

Without annotations, the description carries full burden. It implies a read operation and details the data returned, indicating non-destructive behavior. However, it does not explicitly state safety or other traits like auth or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single clear sentence with a parenthetical note, no wasted words. It front-loads the core purpose and is appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description provides a high-level list of return data but lacks structural details (e.g., format, nesting). It is adequate but could be more complete for an agent to fully understand the response.

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

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

Schema coverage is 100%, so the schema already fully describes the apiKey parameter. The description adds no additional meaning or context for the parameter, meeting the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a deliverability summary, listing specific components (sending reputation, domain authentication, bounce/complaint health). It is distinct from sibling tools, none of which focus on deliverability.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description only mentions the Deliverability Hub plan requirement, but does not provide explicit guidance on when to use this tool over alternatives or when not to use it. No comparisons or exclusions are given.

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

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

With no annotations, the description carries the full burden of disclosure. It effectively communicates that the tool performs a read operation and returns a message with its event timeline. No contradictions or missing behavioral traits are apparent, but it could be slightly improved by mentioning what is not included.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that conveys the essential purpose without extraneous information. Every word earns its place, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple parameter set, lack of an output schema, and no annotations, the description provides adequate context. It tells the user exactly what to expect (a single message with full timeline). Minor points like response format or error handling are not specified but are not critical for a straightforward fetch operation.

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

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

Schema coverage is 100% and both parameters (id and apiKey) are self-explanatory from their descriptions. The tool description adds no additional semantics beyond the schema, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Fetch', the resource 'single message', and the specific content 'full event timeline', which distinguishes it from sibling tools like list_messages or get_message_events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description does not provide explicit guidance on when to use this tool versus alternatives, such as get_message_events. It only implies the use case of fetching a single message with events, but lacks 'when not to use' or comparative context.

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

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

No annotations are provided, so the description must carry the burden. It states that the tool returns delivery event timeline and excludes body/recipient details, which is good, but it does not disclose any additional behavioral traits like authentication needs, error handling, or performance characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, concise sentence with no filler. Every word adds value, clearly stating the purpose and scope.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, no nested objects, no output schema), the description adequately explains what the tool returns and its limitation. However, it could mention if events are returned in order or paginated, which would improve completeness.

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

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

Schema coverage is 100% with parameters id and apiKey described in the schema. The description adds no additional meaning beyond what the schema already provides, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Get') and resource ('delivery event timeline for a message'), and explicitly distinguishes itself from siblings by stating 'no body or recipient details', making it clear what this tool does versus related tools like get_message.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage for fetching only the event timeline without body or recipient details, but it does not explicitly say when to use this tool over alternatives or provide when-not-to-use guidance. The context is clear but not directive.

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

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

With no annotations, the description carries the burden of disclosing behavior. It mentions including 'EmailContent JSON' in the response, which is helpful. However, it does not disclose that this is a read-only operation, any authentication requirements (though apiKey is in schema), or rate limits. The description is adequate but could be more comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence that conveys the essential information without any fluff. It is front-loaded with the action and resource, and efficiently communicates the key detail about the response content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (2 params, no nested objects, no output schema), the description sufficiently explains the input (templateId) and the key aspect of the output (includes EmailContent JSON). It does not explain other potential response fields or error conditions, but for a read operation with such a narrow focus, it is nearly complete.

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

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

Schema coverage is 100%, with both parameters described in the schema (apiKey: string for overriding env var; templateId: string, slug). The description adds that the tool gets by ID, which aligns with the schema, but does not provide additional meaning or constraints beyond the schema's own descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get a single starter template by ID') and includes the resource type and what is included in the response ('EmailContent JSON'). It distinguishes from sibling tools like list_templates which fetch multiple templates. However, the term 'starter template' is not explained, and it might be unclear if this works for templates that are not starter templates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides no guidance on when to use this tool versus alternatives (e.g., list_templates for a list, or design_email_template for modifying). There are no explicit conditions or exclusions stated, leaving the agent to infer usage from the name alone.

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

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

No annotations are provided, so the description must carry the full burden. It states 'Get' indicating a read operation, but does not mention any behavioral traits such as permission requirements, rate limits, or side effects. With zero annotation coverage, this minimal description lacks sufficient behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, efficient sentence that conveys the core purpose without any superfluous words. It is appropriately front-loaded and concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no required parameters, 1 optional parameter, no output schema), the description provides the essential purpose. However, it lacks details about the output structure or properties. For a simple get operation, this is mostly complete but could hint at what fields are returned.

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

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

The single parameter 'apiKey' is fully described in the schema with a description. The tool description adds context about overriding the environment variable, which is helpful. Since schema coverage is 100%, the description adds slight value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves the current workspace associated with the API key. Its verb 'Get' is specific, and the resource 'workspace' is distinguished from sibling 'list_workspaces' by noting it's the one the API key belongs to.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies use when needing the current workspace, but does not explicitly state when to use this over alternatives like 'list_workspaces', nor does it mention prerequisites or exclusions. Thus, only implied usage guidance.

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

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

No annotations are provided, so the description carries the full burden. It accurately conveys a read operation returning usage metrics for the current month, but lacks details on security, rate limits, or side effects. Adequate but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence with no waste. Front-loads the action and the key data items, making it efficient for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with one optional parameter and no output schema, the description sufficiently outlines the return values (send count, contact count, plan limits). Could be considered complete enough for correct agent invocation.

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

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

Schema coverage is 100% with a single parameter (apiKey) already described in the schema. The tool description adds no extra meaning beyond what the schema provides, meeting the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'get' and the resource 'workspace usage', listing specific data returned (send count, contact count, plan limits). It is distinct from sibling tools like 'get_workspace' or other list tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives. No prerequisites, context, or exclusions are mentioned, leaving the agent without situational advice.

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

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 mentions CSV import and tag application but does not clarify error handling, idempotency, rate limits, or authentication details beyond the apiKey parameter. The updateExisting behavior is implied but not elaborated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, no fluff. Every sentence provides essential information: the action and format, then the minimum requirements and optional tags. Highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no output schema, and no annotations, the description covers the core functionality but misses details like return value, batch limits, or error behavior. It is adequate for a simple import tool but not thoroughly complete.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds value by clarifying that each CSV row must have an email column and that tags apply to all imported contacts, which goes beyond the schema's parameter descriptions. However, it does not explain the CSV format in detail beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Bulk import'), the resource ('contacts'), and the data format ('CSV data'). It also specifies the minimum requirement (email column) and the ability to apply tags, making the tool's purpose distinct from sibling tools like create_contact (single contact) or add_contacts_to_audience (add to audience).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage for bulk imports but does not explicitly contrast with other contact-related tools (e.g., create_contact for single contacts, add_contacts_to_audience for adding to audiences). It lacks when-to-use or when-not-to-use guidance, relying on the user to infer from the sibling list.

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

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

No annotations are provided, and the description does not disclose behavioral traits such as read-only nature, required permissions, rate limits, or pagination. The description carries the full burden but fails to add significant transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is two sentences, front-loaded with the purpose. The second sentence adds context about what Actions are, though it could be slightly more focused. Efficient overall.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, and the description does not mention what the response contains, pagination, or limiting factors. For a simple list tool, it leaves out important context about return values and potential filtering.

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

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

Schema description coverage is 100%, so baseline is 3. The description does not add extra context beyond what the schema provides for the apiKey parameter. It is adequate but not enhanced.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List Actions' and explains what Actions are (event->template pairings). This distinguishes it from sibling tools like get_action and create_action, though it could be more explicit about the resource scope (all actions in workspace).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use list_actions vs get_action or other siblings. No mention of prerequisites, filters, or context for choosing this tool over alternatives.

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

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

No annotations are provided, so the description must carry the full burden. It does not disclose whether results are paginated, sorted, or require authentication (the apiKey parameter is optional). The description adds minimal behavioral context beyond the action itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description uses only two sentences, with no unnecessary words. Every sentence adds value: the first states the action, the second defines the resource. It is perfectly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is adequate for a simple list tool, defining the resource. However, it lacks information about the response format, pagination, or any ordering. Given no output schema, these details would enhance completeness.

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

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

With 100% schema description coverage, the baseline is 3. The description does not add any additional meaning to the apiKey parameter beyond what the schema already provides (overrides env var).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'list' and resource 'audiences', and defines what an audience is ('static, manually-managed group of contacts'), distinguishing it from related concepts like segments. It is specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage for retrieving all audiences but provides no explicit guidance on when to use this tool vs siblings (e.g., list_segments) or when not to use it. No prerequisites or alternatives are mentioned.

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

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

No annotations provided, and description lacks behavioral details such as pagination (cursor parameter not explained), authentication (apiKey only hinted), rate limits, or whether it returns full enrollment objects. Insufficient disclosure for a list endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence, front-loaded with key information, no unnecessary words. Highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters and no output schema or annotations, description is incomplete. Missing explanation of pagination, filter options, return format, and required state parameter behavior. Not sufficient for an agent to use correctly without additional hints.

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

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

With only 40% schema description coverage, description does not compensate. Does not explain state enum values, cursor usage, or limit meaning beyond what schema provides. The mention of 'active and historical' only vaguely hints at the state filter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verb 'List' and resource 'enrollments for an automation', clarifying scope with 'active and historical'. Clearly distinguishes from siblings like 'enroll_in_automation' and 'list_automations'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives like 'list_automations' or 'get_automation_stats'. No prerequisites or exclusions mentioned.

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

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

No annotations provided, so the description carries the full burden. It lists status and trigger types but does not disclose whether the operation is read-only, authentication requirements, rate limits, or what happens if the workspace is empty. The word 'List' implies idempotency, but that is not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single concise sentence front-loading the core purpose and key details (status and trigger types). No unnecessary words; every phrase earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should indicate what the response contains. It mentions status and trigger types but not the full structure, pagination, or ordering. Adequate for a simple list tool, but could be more complete.

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

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

Schema coverage is 100%, and the schema already describes the single parameter 'apiKey' with its purpose. The tool description does not mention parameters, so it adds no additional meaning. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the action (list), resource (automations), scope (workspace), and additional details (draft/active/paused status and trigger types). Effectively distinguishes from sibling tools like 'get_automation' (single) and 'get_automation_stats' (statistics).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Implied usage: use when you need an overview of all automations. However, no explicit guidance on when to use this versus alternatives like 'get_automation' for details, nor any exclusions or conditions.

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

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

With no annotations, the description must disclose behavior. It states listing with filtering and pagination, which is clear but lacks details on authentication, rate limits, or result shape. It is adequate but not thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence with no extraneous information. Every word contributes value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 optional parameters and no output schema, the description is minimal. It does not explain return format, error handling, or pagination behavior beyond what the schema provides. Adequate but not complete.

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

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

Schema description coverage is 100%, so each parameter is already documented. The description reinforces the purpose of status and pagination but adds no new meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'List email campaigns with optional status filtering and pagination' uses a specific verb-resource pair, clearly distinguishing it from sibling tools like list_actions or list_audiences.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance is provided on when to use this tool versus alternatives such as list_campaign_stats or get_campaign_stats. The description does not mention exclusions or context for usage.

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

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

No annotations provided, so description must carry full burden. Only mentions pagination and filtering, but fails to disclose authentication, rate limits, or return value structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two succinct sentences that front-load key information. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a simple list tool but lacks details on result ordering, total count, or default behavior. No output schema, so more context would help.

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

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

Schema has 100% description coverage; description mentions subscription status and tag but adds no new semantics beyond what schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it lists contacts with optional filters. However, no distinction from sibling search_contacts, which may have similar purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus search_contacts or other list tools. Alternatives are not mentioned.

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

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

No annotations are provided, so the description carries full burden. It discloses the core behavior (listing with filters) but omits details like default sorting order, rate limits, or whether deleted conversations are excluded. The mention of 'unified inbox' adds context but is not directly behavioral.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two concise sentences cover the main purpose. The first sentence front-loads the action and filters. However, the second sentence about 'Send16's unified inbox' is slightly vague and could be replaced with more concrete behavior (e.g., pagination details).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema is provided, yet the description does not explain what is returned (e.g., conversation IDs, subjects, timestamps). Pagination parameters (limit, offset) are in schema but not described in terms of behavior (e.g., 'returns results in reverse chronological order'). For a listing tool, this is a notable gap.

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

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

Schema coverage is 100% with all parameters described. The tool description merely echoes the filter options without adding extra semantic meaning. Baseline of 3 is appropriate since schema already documents parameters well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'List inbox conversations' with explicit filtering options (state, mailbox, label, screener status, full-text search). It distinguishes from sibling tools like get_convo (single conversation) and list_messages (messages within conversations).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides basic use cases (listing with filters) but lacks guidance on when to use alternatives (e.g., search_contacts, list_inbox_counts) or when not to use this tool. No mention of pagination behavior or prerequisites.

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

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

With no annotations, description carries full burden. It states what the tool returns but does not disclose read-only nature, authentication requirements beyond parameter, or any side effects. Adequate but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence is concise and front-loaded with core action and included details. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with one optional parameter and no output schema, description is largely complete. Could mention return format or authentication reliance, but not critical.

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

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

Schema coverage is 100% for the single parameter (apiKey). Description adds no additional meaning beyond schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verb 'List' and resource 'sending domains', and specifies included information (verification status and DNS records). Clearly distinguishes from related sibling tools like add_domain and check_domain_health.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Description provides no guidance on when to use this tool vs alternatives (e.g., check_domain_health for individual domain health). Lacks context for appropriate usage scenarios.

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

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

No annotations provided, so description carries full burden. It lacks disclosure of authentication requirements, read-only nature, rate limits, or idempotency. The description is minimal on behavior beyond the action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence, front-loaded with essential information, no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Describes output as counts per category and label, but lacks details on output format (e.g., object structure, array). Without output schema, a bit more detail would improve completeness.

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

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

Schema coverage is 100% with one parameter fully described in the schema. Description adds no additional meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'Get' and specific resource 'unread/total counts per category and label for the inbox sidebar', listing categories. Distinguishes from sibling tools as no other tool relates to inbox counts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Implied usage for inbox sidebar counts, but no explicit guidance on when to use vs alternatives. No exclusions or when-not-to-use mentioned.

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

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

No annotations are provided, so the description must disclose behavioral traits. It does not mention pagination, default ordering, rate limits, or the return format. The description only restates filtering capabilities without additional behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that efficiently communicates the tool's purpose and key features without extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers core filtering but omits important context like pagination behavior (though limit/offset params exist), default values, and the structure of the returned data (no output schema). Adequate but could be more complete.

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

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

Schema coverage is 100% with each parameter having a description. The description summarizes filterable parameters but adds no new meaning beyond the schema. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies a clear verb ('list'), resource ('messages from the unified send log'), and scope ('transactional + campaign'), uniquely distinguishing it from siblings like get_message or other list_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description lists filter dimensions but does not explicitly state when to use this tool vs alternatives like get_message for a single message or list_campaigns for campaigns. Usage context is implied but not made explicit.

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

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

The description explains that segments compute their members dynamically, which is a key behavioral trait. However, it does not address permissions, rate limits, pagination, or return format, leaving gaps for an agent without annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences with zero waste, front-loaded purpose, and efficient communication. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one optional parameter and no output schema, the description explains what the tool lists and the nature of segments. Missing details on output format or potential limitations, which would help completeness.

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

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

Schema coverage is 100% for the single parameter (apiKey), so the schema already documents it. The description adds no additional meaning beyond the schema, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'list dynamic segments' and distinguishes from siblings by noting they compute members from a filter expression. However, it does not explicitly differentiate from other list tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus alternatives like list_audiences or list_contacts. No prerequisites or exclusions mentioned.

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

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

No annotations provided, so the description must disclose behavioral traits. It does not mention that the tool is read-only, required authentication, rate limits, or any side effects. The description is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, concise sentence that efficiently communicates the tool's purpose. No unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is too minimal for a list tool with pagination parameters and no output schema. It lacks information about return format, pagination behavior, or what fields are included in the response.

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

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

Schema parameter description coverage is low (25% for apiKey). The description adds value by listing the reason enum values, clarifying what they represent. However, it does not explain limit or offset parameters, nor their role in pagination.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists suppressed email addresses and specifies the four reason types (bounces, complaints, unsubscribes, manual). It distinguishes from sibling tools like add_suppression and remove_suppression which are mutation operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance on when to use this tool versus other list tools (e.g., list_contacts, list_audiences) or when not to use it. The description merely states what it does without context for selection.

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

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

No annotations are provided, so the description must carry the full burden. It only states the action without disclosing authentication needs, rate limits, pagination, or response format. For a simple list operation, more context is needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, concise sentence with no wasted words. It is front-loaded with the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema and annotations, the description is too brief. It does not explain return values, whether pagination exists, or any edge cases. More context is needed for a complete understanding.

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

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

The only parameter, apiKey, is described in the schema. The description adds no further meaning beyond the schema, and schema coverage is 100%. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (List), the resource (email templates), and the scope (starter-gallery available to every workspace). It distinguishes from siblings like get_template and other list_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies the tool is for listing pre-made templates, but lacks explicit guidance on when to use this tool vs alternatives like get_template, design_email_template, or list_campaigns. No when-not or alternative tool mention.

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

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

No annotations are provided, so the description carries full burden. It only states basic purpose without disclosing behavior like pagination, ordering, or rate limits. For a read operation, more detail is needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two efficient sentences: first states action, second defines topics. No wasted words, but could be slightly more structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with one optional param and no output schema, the description explains the concept. Lacks mention of response format or sorting, but adequate.

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

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

Schema has 100% coverage with one parameter (apiKey). The description does not add parameter semantics beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it lists subscription topics and explains what topics are (granular categories). This distinguishes it from sibling list tools like list_campaigns or list_automations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Description implies usage for viewing topics used in gating (campaigns, automations) but does not explicitly state when to use or avoid, nor does it mention alternatives among siblings.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It only states the tool lists webhooks, with no mention of pagination, rate limits, or any side effects. This is minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, no unnecessary words. The description is front-loaded with the core action and adds one contextual detail (plan feature). Efficient and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with one optional parameter and no output schema, the description is adequate but lacks details about what the response includes (e.g., webhook details like URL, events). It could be more complete by mentioning typical return fields.

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

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

The input schema has one optional parameter (apiKey) with 100% schema description coverage. The tool description does not add any additional meaning about the parameter, but the baseline of 3 is appropriate since the schema already covers it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists configured outgoing webhooks, which is a specific verb and resource. However, it does not explicitly differentiate from sibling tools like create_webhook or delete_webhook, though the verb 'list' naturally sets it apart.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage by indicating the tool lists webhooks and that webhooks are a plan feature. It provides no explicit guidance on when to use this tool versus 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.

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

No annotations are provided, so the description carries full burden. It discloses the tool is read-only and scope-limited, but lacks details on pagination, rate limits, or response format. For a simple list tool, the transparency is adequate but not enhanced beyond the basic function.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, concise sentence that front-loads the key action and scope. No unnecessary words, earning its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has low complexity with one optional parameter and no output schema. The description covers purpose and access scope but does not explain return values or any list behavior (e.g., ordering, filtering). Given no output schema, more detail would improve completeness.

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

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

Schema coverage is 100% with one parameter (apiKey) well-described in the schema. The description adds no additional meaning beyond this, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists workspaces the authenticated user has access to, with explicit scope 'owner or member'. The verb 'list' and resource 'workspaces' are specific, and it distinguishes from sibling 'get_workspace' which retrieves a single workspace.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage when needing to see all accessible workspaces, and the scope ('owner or member') provides context. It does not explicitly mention when not to use or alternatives, but for a list tool, this is sufficient context.

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

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

With no annotations, the description carries full burden but only states the basic action. It fails to disclose behavioral traits like idempotency, side effects, permissions, or what 'read' means in terms of state changes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence that is front-loaded and contains no wasted words. It efficiently communicates the tool's core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema, the description should hint at return values or success/failure behavior, but it does not. It also provides no context about the system's conversation state or viewer concept, leaving the agent with incomplete information.

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

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

Schema description coverage is 100% (both parameters have descriptions in the input schema). The tool description adds no additional meaning beyond what the schema already provides, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('mark a conversation as read') and target resource ('conversation'), with a specific scope ('for the current viewer'). It distinguishes from sibling tools like 'update_convo' which is broader.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance is provided on when to use this tool versus alternatives such as 'update_convo' or 'get_convo'. There is no mention of prerequisites or contexts where this tool is preferred.

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

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

No annotations exist, so the description must carry full behavioral weight. It accurately states that enrollments freeze and no new contacts enroll, but does not disclose reversibility, permissions, or effects on other automations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two concise sentences deliver the core purpose and key behavioral detail with no superfluous words. Front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, no output schema), the description covers the essential behavior. However, it could mention that the action is reversible or provide a pointer to 'activate_automation' for resuming.

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

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

Schema coverage is 100%, so the schema already documents both parameters ('apiKey' and 'automationId'). The description adds no additional semantic meaning beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Pause') and resource ('automation'), and adds distinct behavioral details ('Existing enrollments freeze in place; no new contacts enroll'). This clearly distinguishes it from siblings like 'activate_automation' or 'resume_campaign'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage for pausing an automation but does not explicitly state when to use it versus alternatives like 'pause_campaign' or 'deactivate_automation', nor does it mention prerequisites or post-conditions.

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

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

With no annotations, description carries full burden. Discloses key behavior: sent messages are unaffected, remaining sends halt. However, could mention reversible nature or permissions needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two sentences, zero waste. Directly states purpose and key behavioral detail. Front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given simple action (no output schema, 2 params), description is complete. Covers what happens to sent and unsent messages, sufficient for agent to understand effect.

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

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

Schema coverage is 100%, and description adds no additional meaning beyond the schema. Both parameters are already described, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb 'pause' and resource 'sending campaign', with explicit scope (already-sent messages unaffected, remaining sends halt). Distinguishes from sibling tools like resume_campaign and pause_automation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

Provides implicit usage context (pausing a sending campaign) but no explicit when-to-use, when-not-to-use, or alternatives. Lacks guidance on prerequisites or side effects.

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

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

No annotations provided, but the description implies a non-destructive read-only analysis by stating it 'surfaces' issues. It does not contradict any known behavior and adequately conveys that the tool performs a review without 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.

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

Two concise sentences: first states the action and second lists the outputs. No extraneous words, front-loaded with the primary purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lacks details about the output format (e.g., structure of returned issues), and there is no output schema to compensate. While it lists what the review surfaces, an agent would benefit from knowing whether results are a list, report, or flags.

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

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

Schema coverage is 100% with clear descriptions for all four parameters. The tool description adds minimal context beyond the schema, such as emphasizing 'email's HTML' and the purpose of audience. Baseline score of 3 is appropriate as the schema already provides sufficient parameter meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with a clear verb 'Run' and specifies the resource 'AI pre-send review on an email's HTML before sending'. It distinguishes itself from siblings by focusing on review rather than sending or design, and lists specific types of issues surfaced.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The phrase 'before sending' clearly indicates when to use the tool (prior to actual send commands). However, it does not explicitly state when not to use it or mention alternative tools for related tasks like previewing recipients or designing templates.

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

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

No annotations are provided, so the description carries the burden. It implies read-only behavior ('Preview') and mentions returning count and sample list, but it does not disclose potential side effects, authentication requirements, or rate limits. Adequate but not thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is two sentences with no unnecessary words. It immediately states the purpose and output, making it efficient and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (2 parameters, no nested objects) and absence of output schema, the description is reasonably complete. It notes the return type (count + sample list), which provides sufficient context for an agent.

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

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

Schema coverage is 100%, so the parameters are already well-described in the schema. The description adds no additional meaning beyond 'campaignId' and 'apiKey'. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Preview' and the resource 'recipient set for a campaign', and specifies output 'Returns count + sample list'. This distinguishes it from sibling tools like send_broadcast or create_campaign.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description mentions 'before sending', implying a pre-send validation use case, but does not explicitly state when not to use it or compare with alternatives like pre_send_review or preview_segment. Guidance is minimal.

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

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

With no annotations provided, the description carries full burden but only states it previews contacts without sending. It does not disclose whether the result is a list, count, or paginated, nor any side effects or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence with no fluff, but it sacrifices detail needed for completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (2 parameters, no output schema), the description provides the basic purpose but lacks detail on what 'preview' returns, making it minimally adequate.

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

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

Schema coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the schema for the two parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the verb 'preview' and specifies the resource 'contacts that match a segment', clearly distinguishing it from sibling tools like preview_campaign_recipients which pertain to campaigns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The phrase 'without sending' implies a read-only context, but there is no explicit guidance on when to use this tool versus alternatives like preview_campaign_recipients or list_segments, nor any prerequisites or exclusions.

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

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

No annotations are provided, so the description bears full responsibility. It mentions 'Returns the new secret once' but fails to disclose that the old secret becomes invalid, any authorization requirements, or rate limits. This is a significant omission for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is two concise sentences with no fluff. It is front-loaded with the action and resource, making it efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 2 parameters and no output schema, the description is minimal. It lacks critical context such as what happens to the old secret, whether there's a grace period, or if the endpoint needs updating. This is insufficient for a security-sensitive operation.

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

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

Schema description coverage is 100% (both parameters apiKey and webhookId are described). The tool description adds no extra meaning to the parameters beyond what the schema provides, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (rotate), the resource (HMAC signing secret for an outgoing webhook endpoint), and the outcome (returns the new secret). It is specific and distinguishes itself from sibling tools like create_webhook or delete_webhook.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The purpose is self-evident from the name and description, but no explicit guidance is given on when to use this tool versus alternatives or when not to use it. The description implies a single use case without exclusions.

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

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

With no annotations, the description carries the full burden of disclosing behavioral traits. It only states 'Remove a contact from an audience' without addressing side effects (e.g., whether it triggers events, idempotency, or if the contact is permanently removed). The parameter apiKey is not explained in terms of its behavioral role beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence that efficiently conveys the core action. It is appropriately sized for a simple operation, with no wasted words. However, it could benefit from slightly more detail without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations, output schema, and minimal description, the tool is only partially complete. An agent lacks information about return values (e.g., success/failure response), side effects, or any confirmation of the removal. This is insufficient for safe invocation.

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

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

Schema description coverage is 100%, so the baseline is 3. The description does not add any additional meaning beyond what the schema already provides for the three parameters (apiKey, contactId, audienceId). Hence, no extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Remove') and the resource ('contact from an audience'), making the tool's purpose unambiguous. It also distinguishes itself from the sibling 'add_contacts_to_audience' by being the inverse operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

No guidance is provided on when to use this tool versus alternatives, such as the inverse 'add_contacts_to_audience' or other removal tools like 'remove_suppression'. There is no mention of prerequisites (e.g., the contact must exist in the audience) 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.