Mailcannon

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

With no annotations provided, the description carries full burden for behavioral disclosure. It only states the basic action without revealing side effects (e.g., whether adding a step to a running campaign affects ongoing sequences) or any other behavioral traits.

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 a single sentence, which is efficient. However, it could be better structured to include more essential information without adding 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 4 required parameters, no output schema, and no annotations, the description is insufficient. It omits the required 'campaignId' and does not explain how the step integrates into a campaign sequence or any return value.

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% (only 'day' has a description). The description adds minimal value: it restates 'delay in hours' for day and lists subject and body without explaining their semantics or constraints. It does not compensate for the low 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 'Add' and the resource 'sequence step', and lists key fields (delay, subject, body). It effectively communicates the primary action, though it does not explicitly distinguish from sibling tools like 'update_campaign_step' 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 provides no guidance on when to use this tool versus alternatives such as 'create_campaign' or 'update_campaign_step'. There is no context about prerequisites, order of steps, or campaign status requirements.

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 carries full burden. It only says 'Add', implying creation, but offers no details on side effects, idempotency, error conditions, or auth requirements. This is insufficient for safe invocation.

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, extremely concise. However, it sacrifices informativeness for brevity. While not verbose, it is minimally adequate but lacks structure or front-loading of critical info.

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 6 parameters, no output schema, and no annotations, the description is vastly incomplete. It omits return values, error handling, usage context, and any behavioral details beyond the basic action.

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 0% and the description adds zero parameter information. Parameter names (e.g., email, firstName) are self-evident, but the description does not explain purpose, constraints, or relationships, failing to compensate for the schema's lack of 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 states 'Add a single contact', which clearly identifies the action (add) and the resource (contact). It distinguishes from sibling 'add_contacts' by specifying 'single', leaving no ambiguity about scope.

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 vs. alternatives like 'add_contacts' (plural). No prerequisites, context, or exclusions provided, leaving the agent without direction.

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 fully disclose behavioral traits. It mentions the max 100 limit but omits side effects, permissions, error handling, or confirmation of successful addition. The description is insufficient 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 a single, well-structured sentence with no redundancy. It front-loads the key constraint (max 100) 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 one parameter with nested objects, no output schema, and no annotations, the description is overly minimal. It lacks details on return values, error cases, and the behavior when contacts are invalid or exceed the limit.

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 0%, and the description adds no meaning beyond the schema's field names. It does not explain the purpose of fields like tags, title, or company, nor the required email and firstName structure.

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 'Bulk add contacts (max 100)', identifying the action (add), resource (contacts), and a key constraint (maximum 100). This distinguishes it from sibling tool 'add_contact', which handles single 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?

The description implies usage for multiple contacts via 'Bulk' and the sibling 'add_contact' suggests a single-contact alternative, but no explicit when-to-use or when-not-to-use guidance is 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?

With no annotations, the description must disclose behavioral traits. It only states 'Add an email provider' without explaining required authentication, side effects, idempotency, or error conditions (e.g., duplicate name). This is severely 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 extremely short (4 words), but it sacrifices informativeness for brevity. It fails to earn its place by providing crucial context, making it under-specified rather than 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 complexity (7 parameters, nested objects, no output schema), the description is grossly incomplete. It does not describe what the tool returns, how parameters interact, or behavioral details, leaving the agent with insufficient 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 0%, but the description adds no meaning to any of the 7 parameters. It does not explain what 'env', 'url', 'args', 'kind', 'name', 'command', or 'transport' represent. Even basic parameter roles are omitted.

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 'Add an email provider' clearly states the verb and resource, distinguishing it from sibling tools like remove_provider and list_providers. However, it lacks specificity about the provider type (email) which is implied but not explicit.

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_providers or create_campaign. There is no mention of prerequisites, limitations, or when not to use this tool.

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 the action without detailing what the check entails (e.g., validation level, read-only nature, or output format).

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 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 the simple input (one parameter) and no output schema, the description is minimally adequate but lacks information about return values 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 description coverage is 100%, and the tool description adds no additional meaning beyond the schema's parameter description. 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 'Check SPF, DKIM, DMARC records for a domain' uses a specific verb and resource, clearly distinguishing it from siblings like 'check_email_spam_score' and 'get_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?

No explicit guidance on when to use this tool versus alternatives; no prerequisites or exclusions 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?

The description lacks behavioral details such as whether this is a read-only operation, what the output looks like, or any side effects. With no annotations, this gap is significant.

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 and front-loaded. However, it could benefit from additional context without adding much 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?

The tool is relatively simple but lacks important details: what the output is (e.g., a score, list of triggers), whether it modifies anything, and usage context. With no annotations or output schema, the description is insufficient for an agent to confidently use.

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 mentions subject and body but provides no additional context such as expected formats, maximum lengths, or examples. Since schema coverage is 0%, the description should fill the gap but does not sufficiently.

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 function: to analyze email subject and body for spam trigger words. It implicitly distinguishes from sibling tools like check_domain_deliverability and check_step_spam_score, which likely operate at different levels.

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 usage context, such as when to prefer this over check_step_spam_score or check_domain_deliverability. There is no indication of prerequisites or limitations.

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 fails to disclose whether the tool is read-only, what side effects (if any) occur, or what the output looks like. The agent cannot infer behavioral traits beyond 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?

Single sentence, front-loaded, and easy to parse. No extraneous information, though the brevity sacrifices detail.

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 only one required parameter, no output schema, and no annotations, the description omits critical context such as return value format, required permissions, and any dependencies. Incomplete for a 'check' type 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 0% and description adds no meaning to the single parameter 'stepId'. It does not explain what constitutes a stepId or how to obtain it, leaving the agent without guidance.

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 checks a campaign step's subject and body for spam triggers. The verb 'check' is specific, and the resource 'campaign step' distinguishes it from sibling 'check_email_spam_score' which checks an email directly.

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 'check_email_spam_score'. The description implies it is for campaign steps, but does not provide context on prerequisites 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 carries full burden, but it only states the action without disclosing behavioral traits such as idempotency, side effects (e.g., triggering workflows), validation, or permission requirements. This leaves significant uncertainty 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?

The description is ultra-concise (6 words), but this comes at the cost of missing critical details. It is not padded with fluff, but the brevity sacrifices utility, making it mediocre.

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 and minimal parameter documentation, the description should compensate but does not. It fails to explain return values, errors, or what constitutes a valid campaign, leaving the agent without enough context to use or debug the 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?

The only parameter 'name' has no description in the schema (0% coverage) and the description adds no extra meaning—no constraints, uniqueness, format, or length. The agent has no information beyond the parameter name.

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 ('Create') and the resource ('a new email campaign'), making the basic purpose evident. However, it lacks differentiation from sibling tools like add_campaign_step or update_campaign, which are distinct in purpose but not contrasted here.

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 schedule_campaign or process_campaigns. There are no prerequisites, exclusions, or context hints to help the agent select this tool appropriately.

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 carries full burden for behavioral disclosure. It only states 'Create a new task' without any details on idempotency, side effects, authorization needs, or error conditions, similar to the LOW calibration example.

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?

At four words, the description is extremely terse. While concise, it is under-specified and lacks necessary context, making it insufficient for an AI agent to understand the tool's full functionality.

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 four parameters with low schema coverage, no output schema, and no annotations, the description is entirely inadequate. It provides no return value information, no preconditions, and no clarity on behavior, leaving the agent with minimal actionable 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 description coverage is only 25% (only dueDate has a description). The tool description adds no meaning beyond parameter names for title, priority, and description. It fails to clarify formats, constraints, or default values for the three undocumented 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 'Create a new task' uses a specific verb and resource, clearly indicating the action and object. It distinguishes from sibling tools like update_task, delete_task, and list_tasks, making the purpose unmistakable.

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. With many sibling tools (add_contact, create_campaign, etc.), the description offers no context for appropriate usage 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?

Without annotations, the description carries full burden. It discloses the cascading deletion of steps, which is a critical behavioral insight. However, it omits other common details like irreversibility, permission requirements, or effect on associated data (e.g., contacts in steps).

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, front-loaded with the action, which is concise. However, it trades off completeness for brevity, lacking details that could be included without significant bloat.

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 is destructive and has no annotations or output schema, the description should provide more context about return values, error states, or preconditions. It covers the cascade but not enough 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?

Input schema has one parameter 'id' with no description and schema coverage is 0%. The description adds no explanation of what 'id' refers to (e.g., campaign ID format, example) leaving the agent to infer meaning from 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?

Description clearly states the action ('Delete') and the resource ('a campaign and all its steps'), distinguishing it from siblings like delete_campaign_step which only deletes a single step.

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 vs alternatives (e.g., pausing instead of deleting), no prerequisites or consequences mentioned. The description assumes the agent knows when deletion 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?

The description only includes the verb 'Delete', which implies destructiveness but offers no additional behavioral context. With no annotations, the description fails to disclose permanence, side effects, or permission requirements, making it minimally transparent.

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 at one sentence, which is efficient but borders on under-specification. It could provide more value with additional context 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 output schema and annotations, the description is incomplete. It does not cover return values, error conditions, or prerequisites, leaving the agent underinformed for a delete operation that may have consequences.

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 sole parameter 'id' has no description in the schema (0% coverage), and the description does not explain what the id refers to (e.g., step ID or campaign-step combination). This leaves the agent without meaningful semantic guidance beyond the type.

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 ('Delete') and the resource ('a step from a campaign'), which differentiates it from sibling tools like 'add_campaign_step' or 'update_campaign_step'. However, it lacks specificity about what constitutes a 'step' in this context.

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_campaign_step' or 'delete_campaign'. There are no mentions of prerequisites or conditions that might make this tool appropriate or 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?

No annotations provided, so description carries full burden. It does not disclose side effects (e.g., cascade delete), idempotency, error behavior (e.g., missing ID), or restrictions (e.g., cannot delete running tasks). For a delete operation, this is a significant gap.

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, terse sentence that conveys the essential action without any fluff. It is appropriately 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 one-parameter delete tool, the minimal description is borderline adequate but lacks behavioral context (error handling, idempotency) that an agent needs for reliable use, especially given no output schema or annotations.

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 0% schema description coverage, the description adds no meaning beyond the schema's 'id' field type. It fails to explain acceptable formats, constraints, or relationships, leaving the agent with minimal guidance for invocation.

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 (Delete), resource (task), and input (by ID), effectively distinguishing it from sibling tools like create_task, update_task, and list_tasks.

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 or when not to use this tool, such as prerequisites (task must exist) or alternatives (e.g., if task has dependencies). The description is purely functional.

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 it 'gets' stats, implying a read operation. It does not disclose any side effects, authentication needs, or rate limits, but is minimally adequate for a simple retrieval.

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 extraneous words. It is front-loaded with the verb and resource, and every part is useful.

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 and no annotations, the description is sufficient for a simple stats retrieval but lacks detail on output format, scope (e.g., which campaign or time period), or any related setup steps.

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 zero parameters, and schema coverage is 100% (empty). The description adds no parameter info, but the baseline for zero parameters is 4, and no additional meaning is required.

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 deliverability statistics and enumerates specific metrics (sent, opens, bounces, replies), which distinguishes it from sibling tools like check_domain_deliverability or check_email_spam_score.

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. There is no mention of prerequisites, context, or exclusions, 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 provided, so the description must disclose behavior. It only states the action without mentioning if it is read-only, requires authentication, or any side effects. Minimal behavioral information.

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?

One short sentence, no wasted words, but it is too minimal for a tool with no annotations or output schema. Conciseness is good, but at the cost of 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?

Despite the simplicity of the tool, the description lacks details on return values, possible keys, or error conditions. Without annotations or output schema, the description is insufficient for an agent to use the tool correctly.

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

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

Schema has 0% description coverage; the only parameter 'key' lacks explanation. The description gives an example 'timezone' but doesn't specify valid keys, format, or how to discover them, leaving the agent to guess.

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 states the verb 'Get' and resource 'user setting' with an example 'timezone', clearly indicating the tool's function. However, it does not explicitly distinguish from sibling tools like 'list_settings' that also retrieve settings.

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_settings' or 'set_setting'. The description 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?

The description does not disclose behavioral traits beyond the basic operation. There are no annotations to fall back on, and the description omits crucial details such as whether the tool is read-only, performance implications (e.g., pagination for large datasets), or any side effects. The agent cannot anticipate the response format or potential errors.

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, focused sentence that front-loads the action and resource. It avoids verbosity but could be slightly expanded with minimal behavioral notes without losing 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?

Given no parameters and no output schema, the description is minimally adequate. It tells what the tool returns, but lacks details on pagination, sorting, or potential limits. For a list tool in a suite with many siblings, more contextual completeness (e.g., 'returns all campaigns, use with caution if many campaigns exist') would be beneficial.

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 tool has no parameters, so the schema description coverage is trivially 100%. The description adds value by stating that the result includes steps, which is not apparent from the empty schema. With zero parameters, a baseline of 4 is appropriate as the description compensates by clarifying the output scope.

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 ('List') and the resource ('campaigns'), and specifies that steps are included. It effectively distinguishes the tool from sibling tools that list other entities (e.g., list_contacts, list_providers) or modify 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 is provided on when to use this tool versus alternatives. There is no mention of prerequisites, exclusions, or context such as 'use this to get an overview before modifying' or 'for filtered lists, use search tools'. This limits its usefulness for an agent deciding 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 provided, and description does not disclose behaviors such as read-only nature, pagination, order, or limits. Minimal info.

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?

Extremely concise at three words, no wasted text, but lacks structure or additional context like 'Returns a list of contacts'.

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 parameterless list-all tool, description is mostly adequate but could mention return format or that it is read-only to be fully 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?

No parameters exist, so description cannot add meaning beyond the schema. Baseline score of 4 applies as there is nothing to compensate for.

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 verb 'List' and resource 'contacts', distinguishing it from sibling tools that add or remove 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 explicit guidance on when to use this tool vs alternatives. It's implied for viewing all contacts, but lacks exclusions or scenarios like filtering.

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; description only states 'list all' which implies read-only, but no additional behavioral details are given.

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, perfectly concise with 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?

Given no parameters, no output schema, and simple task, the description is complete enough for an agent to understand its purpose.

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?

No parameters; schema coverage is 100%, and baseline for 0 parameters is 4.

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 verb 'List' and resource 'email providers'. Distinguishes from sibling tools like add_provider and remove_provider.

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 specific usage guidance provided, but the tool is straightforward and the need for 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?

No annotations present, so description carries full burden. It implies read-only behavior but does not disclose if results are limited to active runs, include pagination, or any side effects. Basic but lacks important behavioral details.

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, 5 words, front-loaded with action and resource. No unnecessary words. 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?

Given no output schema and no annotations, the description is bare minimum. It tells what it does but does not explain output structure, ordering, or filtering. 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?

Input schema has zero parameters, so baseline is 4. Description adds no extra parameter info, which is acceptable since there are no parameters to document.

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 verb 'list' and resource 'scheduled campaign runs', distinguishing it from sibling tools like 'list_campaigns' and 'schedule_campaign'. However, 'scheduled campaign runs' could be more precise about scope (e.g., including future only?).

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. Sibling tools like 'list_campaigns' might overlap, and 'schedule_campaign' is related but not explained. No mention of 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 provided, so the description carries the burden. It indicates a read-only list operation, but does not mention safety, sensitivity of settings, or response behavior.

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, no redundancy, directly communicates the tool's 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?

With no output schema, the description does not explain return values or format. It is adequate for a simple list operation but could provide more detail about what 'user settings' includes.

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?

There are zero parameters and schema coverage is 100%. The description adds no parameter info, but none is needed; baseline 4 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 'List all user settings' clearly states the action (List) and resource (user settings), and distinguishes from sibling tools like get_setting and set_setting.

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 vs alternatives, but the context with siblings implies it for listing all settings, while get_setting retrieves a single one.

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 full burden. It only states the basic function without detailing behavior such as performance, sorting, or uniqueness guarantee.

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, minimal and to the point. 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?

Adequate for a zero-parameter tool with no output schema, but lacks details about the output format or what constitutes a 'tag'. Could explain return structure or limitations.

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?

No parameters exist, so schema coverage is 100%. The description adds minor value by specifying 'across your contacts' (scope), but does not introduce new parameter-level details 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's action ('List all unique tags') and scope ('across your contacts'). It distinguishes from sibling tools like update_contact_tags by focusing on read-only listing.

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 vs alternatives (e.g., update_contact_tags for modifying tags). No context on prerequisites or appropriate 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 are provided, so the description must disclose behavioral traits. It only states 'List all tasks,' which implies a read operation but offers no details on permissions, rate limits, or what 'all tasks' entails (e.g., scope across users or workspaces).

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 at three words, which is efficient for a tool with no parameters. However, it is slightly under-specified, lacking any additional context that could be added without losing 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?

Given no output schema or annotations, the description is the sole source of context. It does not specify return format, pagination, or filtering capabilities. For a tool named 'list_tasks' with siblings for task management, 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?

The input schema has no parameters, and schema coverage is trivially 100%. The description adds no parameter-level information, which is acceptable since none exist. The baseline of 3 applies as the description does not need to compensate.

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 the resource 'tasks', making the primary action and target obvious. However, it does not distinguish this tool from other list tools among siblings, such as list_campaigns or list_contacts, so it lacks differentiation.

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. There is no mention of prerequisites, context, or exclusions. The description simply says 'List all tasks' without any usage 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 only states the action and immediate effect. It does not disclose reversibility, side effects (e.g., impact on scheduled sends), or any prerequisites, leaving behavioral gaps.

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 action and effect. Minor improvement could be adding a separate line for the parameter, but overall 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 tool (1 param, no output schema), the description is marginally adequate for the purpose but lacks parameter details and usage context. It does not fully compensate for missing annotations.

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 0% description coverage for the single required parameter 'id', and the description does not explain what 'id' refers to (e.g., campaign ID). The description fails to add 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 clearly states the action 'Pause a campaign' and the effect 'stops processing all active schedules', distinguishing it from siblings like 'resume_campaign' and 'schedule_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?

No guidance is provided on when to use this tool versus alternatives, such as whether the campaign must be active or what happens if already paused. The description lacks usage 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 fully convey behavioral traits. It states it processes due schedules but does not explain what 'process' entails (e.g., sending emails, mutating state, side effects), leaving significant ambiguity for an AI agent.

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 with a single sentence, but its brevity sacrifices clarity on usage and behavior, preventing a higher score.

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 likely performs actions (processing campaigns) and lacks an output schema, the description fails to explain return values, side effects, or prerequisites, making it incomplete for reliable 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?

With 100% schema description coverage for the only parameter, the description's mention of includeFailed adds no new meaning beyond the schema's description, meeting the baseline but not exceeding 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 specifies the verb 'process' and the resource 'campaign schedules', and distinguishes the tool's action of processing due schedules from sibling tools like pause/resume/retry_failed by noting the option to retry failed ones.

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 processing due campaign schedules and mentions the includeFailed parameter for retrying failed ones, but does not explicitly compare with sibling tools like 'retry_failed' or provide conditions when not to use this tool.

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. The description does not disclose behavioral traits like whether removal is permanent, any side effects, or required permissions.

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, front-loading the action and resource. While brief, it is not verbose, but could benefit from slight expansion.

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 one-parameter tool with no output schema, the description is minimally complete. However, it does not mention that the ID is required (though schema shows it) or any 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 description coverage is 0%. The description says 'by ID' but adds no semantics beyond the parameter name and type string. No format or constraints explained.

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 'Remove' and resource 'contact', and specifies identification by ID. It distinguishes from sibling tools like add_contact and list_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, such as update_contact_tags or delete_campaign. 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?

With no annotations provided, the description must fully disclose behavioral traits. It only states 'Remove' without clarifying if this is a permanent deletion, whether confirmation is needed, or any side effects. Inadequate for a mutation operation.

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 substance. While brevity is valued, this does not earn its place as it provides minimal useful 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 deletion tool with no output schema and no annotations, the description is critically incomplete. It fails to mention whether removal is permanent, any related entities affected, or expected return values. Does not satisfy the needs of 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 0%, and the description adds no meaningful detail beyond the parameter name 'id'. It does not explain what constitutes a valid ID, any constraints, or the effect of the parameter. The phrase 'by ID' merely restates 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 action (Remove), the resource (provider), and the method (by ID). It is specific enough to distinguish from other tools that operate on different resources, though it does not explicitly differentiate from similar 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?

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no caveats. It simply states the operation without 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 must carry the burden of behavioral disclosure. It reveals the main effect (reactivating paused schedules) but does not mention potential side effects, error conditions, or required permissions. The core behavior is covered, but details are 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 sentence with no wasted words. It efficiently communicates the tool's 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 one parameter, no output schema, and no annotations, the description adequately covers the core functionality. It could mention that the campaign must be paused or clarify return behavior, but for a simple resume operation, 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 description coverage is 0%, so the description should compensate for the 'id' parameter. However, it does not explain what 'id' refers to (e.g., campaign ID) or provide format/source guidance. The single parameter is common, so missing clarification is a notable gap.

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 'resume a paused campaign' and specifies the resource (campaign) and scope ('reactivates all paused schedules'). This distinguishes it from the sibling tool 'pause_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 the tool is used on paused campaigns, but does not explicitly state when to use it versus alternatives like 'pause_campaign' or 'schedule_campaign'. No guidance on prerequisites or conditions is 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?

With no annotations, the description carries full burden. It only says 'reset all failed schedules to active', but doesn't disclose scope (all schedules in system?), side effects (resumes mass emails?), or whether it's destructive. Minimal transparency 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?

Single sentence with no fluff. Verb first, clear object and result. 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 that resets all failed schedules, the description lacks context on what constitutes 'failed', whether it affects all campaigns or a subset, and any confirmation or rollback. Incomplete given potential impact.

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?

No parameters exist, so schema coverage is 100%. Description doesn't need to explain params, but adds no extra semantic value beyond the schema. Baseline 4 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 uses specific verb 'reset', resource 'failed schedules', and states the outcome 'to active for retry'. It clearly distinguishes from siblings like resume_campaign which works on active schedules.

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 when-to-use or when-not-to-use guidance. Does not mention prerequisites (e.g., need failed schedules) or alternatives like resume_campaign. The description alone doesn't help an agent decide this is the right tool.

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, yet the description fails to disclose behavioral traits such as side effects (e.g., does scheduling overwrite existing schedules?), required permissions, or whether the action is reversible. 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?

The description is a single, concise sentence that front-loads the core purpose. However, it is perhaps too terse, lacking context that could be added without significant verbosity.

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 5 parameters, no output schema, and no annotations, the description is insufficiently complete. It omits details on scheduling semantics, required setup, and expected behavior, leaving the agent underinformed.

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 80%, so baseline is 3. The description adds no additional parameter semantics beyond the schema; it does not explain interactions between parameters like tags vs contactIds.

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: assign contacts to a campaign and schedule it. It distinguishes from siblings like create_campaign (creation) and add_campaign_step (steps), making the purpose unambiguous.

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

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 add_contacts or create_task. The description does not specify prerequisites, scenarios, 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?

With no annotations, the description carries full transparency burden. It states the tool sends an email to the user, but fails to disclose behavioral traits such as whether it requires an active provider, potential delays, or side effects (e.g., triggering spam checks). The optional providerId parameter suggests dependency on a provider, yet this is not mentioned in the description.

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 of 10 words), which would be appropriate only if all necessary details were captured. However, given the missing parameter descriptions and behavioral context, the conciseness results in under-specification. Every sentence should earn its place, but this one misses critical 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 tool with 3 parameters (2 required) and no output schema or annotations, the description is incomplete. It does not explain what happens upon success, how the user receives the test email, or any error scenarios. The agent cannot determine prerequisites (e.g., configured provider) or the tool's scope relative to siblings.

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 33% (only providerId has a description). The description adds no information about parameters like 'subject' or 'body', leaving the agent to infer their meaning from names alone. For a low-coverage schema, the description should compensate by describing parameter roles, formats, or constraints, but it does not.

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 sends a test email to the user for formatting preview. The verb 'send' and resource 'test email' are specific. However, it does not explicitly distinguish from sibling tools like check_email_spam_score, but the unique target 'to yourself' provides implicit differentiation.

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. The description implies the tool is for previewing formatting, but it does not specify prerequisites (e.g., having a configured email provider) or exclude scenarios where this tool is inappropriate. Sibling tools include other email-related actions, but no comparative information is 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 full burden but only states it sets a setting. It does not disclose side effects, permissions, rate limits, or idempotency. Minimal behavioral disclosure 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?

The description is one short sentence with an example, very concise. It could be slightly more structured (e.g., separate general description and parameter details), but it 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 simplicity of the tool (two string params, no output schema) and zero schema coverage, the description is incomplete. It lacks details on valid setting keys, value constraints, persistence, and error conditions. More context is needed 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 0%, so the description must compensate. It provides an example (key='timezone', value='America/New_York') but no explanation of valid keys, value formats, or constraints for the two string parameters. Insufficient semantic help.

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 'Set' and resource 'a user setting' with a concrete example, making it clear what the tool does. It distinguishes from sibling 'get_setting' implicitly, but does not explicitly differentiate from other update 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 gives an example (timezone) implying when to use, but lacks explicit guidance on when to use this tool versus alternatives like 'list_settings' or 'get_setting'. No when-not or prerequisites 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?

There are no annotations, so the description carries the full burden. It states 'update' implying mutation, but omits any behavioral details like permissions, reversibility, or 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?

The description is very concise with one sentence, earnestly stating the sole purpose. However, it could be slightly more informative 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 output schema, annotations, and parameter descriptions, the description is incomplete. It fails to address return values, error cases, or update behavior.

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 0%, yet the description only mentions 'name' without explaining its constraints or the 'id' parameter. It adds minimal 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 clearly states the tool updates a campaign's name, specifying the verb and resource. It distinguishes from sibling tools like create_campaign or delete_campaign, though it could be more explicit about the scope.

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 (e.g., when to update vs create). The description lacks context for choosing this tool 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 exist, so the description bears full responsibility for behavioral disclosure. It only states that fields are updated, but does not specify whether updates are incremental or overwrite all fields, what happens to unspecified fields, whether id validation occurs, or any error scenarios. This leaves significant ambiguity.

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 of nine words efficiently conveys the tool's purpose without redundancy. Every word contributes to understanding, and the structure is front-loaded with the 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?

Given the lack of annotations and output schema, and low schema coverage, the description is insufficient for an agent to use the tool confidently. It omits behavior like whether partial updates are supported, response format, and error conditions. A more complete description would include these details.

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?

Only 25% of schema parameters have descriptions (only 'day' says 'Delay in hours'). The description merely lists parameter names without adding meaning beyond the schema. For example, it does not clarify that 'body' might be HTML or plain text, or that 'day' could be negative or non-integer. The description does not compensate for the low 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 tool's action ('Update') and the specific resource ('a campaign step') along with the editable fields ('day, subject, or body'). It distinguishes from sibling tools like add_campaign_step and delete_campaign_step, which are for different actions on the same resource.

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 that this should be used for existing steps, nor does it contrast with add_campaign_step or update_campaign. The agent must 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?

Without annotations, the description bears the burden. It discloses the replacement behavior, which is crucial for agents to avoid accidental data loss. However, it omits other behavioral details like permissions, side effects, or return 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?

Extremely concise: two sentences, front-loaded with the verb, no wasted words. Every part 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?

For a simple two-parameter tool, the description covers the essential purpose and the key behavioral nuance (replacement). Could be improved by clarifying the 'id' parameter, but overall complete enough 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?

With 0% schema description coverage, the description should compensate. It adds no explanation for 'id' or 'tags' beyond what the schema implicitly shows. No format, examples, or constraints.

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 'Set tags on a contact' and the critical behavioral note 'replaces all tags', distinguishing it from sibling tag tools like list_tags.

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., add_contacts or other tag manipulation). Lacks context on prerequisites or typical use cases.

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 fails to disclose behavioral traits such as idempotency, side effects, error handling (e.g., missing id), or whether updates are partial. Only states 'Update' without 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?

Single sentence, no filler. However, could add essential details without much extra length. Front-loaded with verb and object.

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 6 params, no output schema, and no annotations, the description is too sparse. Does not explain return value, error conditions, or differentiate from similar update tools (e.g., update_campaign_step).

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 0% with 6 parameters. Description only mentions 'status, priority, or fields', leaving out key params like id, title, dueDate, description. Provides limited meaning beyond enum values for status and priority.

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 states verb 'Update' and specific resources: 'task's status, priority, or fields'. Clearly distinguishes from sibling tools like create_task (create) and delete_task (delete).

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 mention of prerequisites, scenarios like partial updates, or when to prefer other tools.

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