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

Annotations declare readOnlyHint=true, indicating a safe read operation. The description adds that it 'returns matched intent topics', hinting at output behavior, but doesn't disclose details like rate limits, authentication needs, or processing time. Since annotations cover safety, the description provides minimal extra context, meeting the lower bar but not enriching behavioral understanding significantly.

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 with zero waste: 'Analyze a website URL and return matched intent topics.' It front-loads the core action and outcome, making it easy to parse. Every word contributes to understanding the tool's function.

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 moderate complexity (analyzing websites for topics), annotations cover safety, but there's no output schema. The description mentions the return value ('matched intent topics'), but doesn't explain format, structure, or potential errors. It's adequate for a read-only tool but lacks depth for full contextual 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 input schema has 1 parameter with 0% description coverage, so the description must compensate. It specifies 'website URL', clarifying the 'url' parameter's purpose beyond the schema's format constraint. However, it doesn't detail URL requirements (e.g., valid protocols, depth limits). With only one parameter, this is sufficient for a high 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?

The description clearly states the tool's purpose: 'Analyze a website URL and return matched intent topics.' It specifies the verb ('analyze'), resource ('website URL'), and outcome ('return matched intent topics'), making the function unambiguous. However, it doesn't differentiate from sibling tools like 'search_topics' or 'list_topics', which prevents a perfect 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, constraints, or compare it to siblings like 'search_topics' or 'get_topic_facets'. Without any usage context, the agent must infer applicability from the tool 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?

Annotations declare readOnlyHint=true, indicating a safe read operation. The description adds context by specifying 'daily trend series', which implies time-series data and a focus on trends over days, but doesn't disclose further behavioral traits like rate limits, data freshness, or output format. With annotations covering safety, this earns a baseline score for minimal added 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, efficient sentence that front-loads the core action ('compare') and resource ('daily trend series for multiple topics'). There's no wasted words or redundancy, making it highly concise and well-structured for quick understanding.

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 moderate complexity (comparing trends), annotations cover safety, but there's no output schema to explain return values. The description mentions 'daily trend series', hinting at time-series output, but doesn't specify format or details. It's adequate for a read-only tool but lacks completeness on behavioral aspects like data scope 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?

With 0% schema description coverage and only one parameter (topicIds), the description compensates by clarifying that it's for 'multiple topics', aligning with the array input. It doesn't detail the integer format or exclusiveMinimum constraint, but for a single parameter, this is sufficient to earn a high score as it adds meaningful context beyond the bare 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 'compare' and the resource 'daily trend series for multiple topics', making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_topic_trend' or 'search_topics', which might also involve topic analysis, so it doesn't reach the highest 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?

The description provides no guidance on when to use this tool versus alternatives. With siblings like 'get_topic_trend' (likely for single topics) and 'search_topics' (possibly for discovery), there's no indication of when this comparison tool is preferred, leaving the agent to guess based on 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 carries the full burden of behavioral disclosure. It states 'create' implies a write operation, but doesn't mention permissions required, whether the creation is idempotent, rate limits, or what happens on success/failure (e.g., returns an audience ID). For a mutation tool with zero annotation coverage, this is a significant gap in 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, efficient sentence with no wasted words. It's front-loaded with the core action ('Create a saved audience configuration'), making it easy to parse. For such a brief statement, it achieves maximum conciseness without being overly terse.

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 (2 parameters with nested objects, no annotations, no output schema), the description is incomplete. It doesn't explain the audience creation process, expected inputs beyond names, what 'config' entails, or the result (e.g., an audience ID). For a tool that likely returns a resource identifier, this leaves critical gaps 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 0%, so the description must compensate by explaining parameters, but it adds no meaning beyond the schema. It doesn't clarify what 'name' or 'config' represent, the purpose of nested fields like 'topicIds' or 'filters', or how they interact. With 2 parameters and complex nested objects, this leaves the agent guessing about usage.

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 ('create') and resource ('saved audience configuration'), which is clear but minimal. It doesn't distinguish this tool from sibling tools like 'update_audience' or 'preview_audience', nor does it specify what an 'audience configuration' entails beyond the name. While it avoids tautology, it lacks specificity about the scope or outcome of creation.

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 siblings like 'update_audience', 'delete_audience', and 'preview_audience', the description fails to indicate prerequisites (e.g., whether an audience must be previewed first), exclusions, or typical workflows. It's a generic statement that offers no contextual 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates something but doesn't mention whether this is a write operation, what permissions are needed, if it's idempotent, or what the expected output might be. This is a significant gap for a creation tool with zero annotation coverage.

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 gets straight to the point with no wasted words. It's appropriately sized and front-loaded, making it easy to parse quickly.

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 2 parameters, 0% schema coverage, no annotations, and no output schema, the description is inadequate. It doesn't explain what a 'tracking pixel' is, what the parameters mean, what happens after creation, or how this tool relates to siblings. More context is needed given the complexity.

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 schema has 0% description coverage, so parameters 'domain' and 'name' are undocumented in the schema. The description only mentions 'domain' generically and doesn't explain what 'name' refers to or provide any semantic context beyond what's implied by the tool name. It fails to 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 action ('create') and resource ('tracking pixel for a domain'), making the purpose immediately understandable. However, it doesn't differentiate this tool from sibling tools like 'update_pixel' or 'list_pixels' beyond the basic verb, missing explicit sibling distinction.

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 like 'update_pixel' or 'list_pixels', nor does it mention prerequisites or context for creating a pixel. Usage is implied by the verb 'create' but lacks explicit when/when-not instructions.

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 the full burden of behavioral disclosure. It states the tool deletes, implying a destructive mutation, but lacks critical details: whether deletion is permanent or reversible, if it requires specific permissions, what happens to associated data, or any rate limits. This is inadequate for a destructive operation with zero annotation coverage.

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—a single sentence with no wasted words. It front-loads the core action ('Delete') and resource, making it easy to parse. Every word earns its place, adhering to best practices for brevity in tool descriptions.

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 destructive nature, no annotations, no output schema, and low schema coverage, the description is incomplete. It fails to address key contextual elements: the impact of deletion, error conditions, return values, or how it fits within the broader audience management workflow. This leaves significant gaps for safe and effective 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 adds minimal semantics beyond the input schema. It specifies that the 'id' parameter refers to a 'saved audience', but with 0% schema description coverage, it doesn't clarify the UUID format or provide examples. Since there's only one parameter, the baseline is higher, but the description doesn't fully compensate for the lack of schema documentation.

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') and resource ('a saved audience by id'), making the purpose unambiguous. It distinguishes from sibling tools like 'create_audience' and 'update_audience' by specifying deletion. However, it doesn't explicitly mention what 'audience' refers to in this context (e.g., marketing audience, user segment), which prevents a perfect 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing audience), exclusions (e.g., cannot delete active audiences), or comparisons to siblings like 'list_audiences' for discovery or 'update_audience' for modification. This leaves the agent with minimal context for decision-making.

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 the full burden of behavioral disclosure. It mentions generating/reusing CSV and returning a signed URL, but lacks details on permissions required, rate limits, whether exports are cached, or if the URL expires. For a tool that likely involves data processing and external access, this is insufficient.

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 front-loads the core action and outcome. Every word contributes meaning without redundancy, making it easy to parse quickly.

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 2 parameters, 0% schema coverage, no annotations, and no output schema, the description is incomplete. It doesn't address error cases, output format details beyond 'CSV', or how the signed URL should be used, leaving significant gaps for an agent to operate effectively.

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 implies 'id' and 'date' parameters relate to 'latest run or a specific date', but doesn't explain what 'id' refers to (e.g., audience ID, run ID) or the format/constraints for 'date' beyond the schema's pattern. This leaves key semantics unclear.

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 ('Generate or reuse a CSV export') and the resource ('audience'), distinguishing it from sibling tools like 'get_audience' or 'list_audiences' that retrieve metadata rather than export data. However, it doesn't explicitly mention what 'audience' refers to in this context (e.g., a marketing audience dataset).

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 'get_audience_results' or 'query_audience', which might retrieve similar data. The description mentions 'latest run or a specific date' but doesn't clarify prerequisites, such as needing an existing audience run from sibling tools like 'list_audience_runs'.

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?

Annotations provide readOnlyHint=true, indicating a safe read operation. The description adds value by specifying what data is retrieved (health, credit, pixels, audience slots), but doesn't disclose behavioral traits like rate limits, authentication needs, or response format. No contradiction with annotations.

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

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

The description is a single, efficient sentence that lists all key data points without unnecessary words. It's front-loaded and every phrase earns its place by specifying the scope of information retrieved.

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 no parameters, annotations cover safety, but no output schema exists. The description adequately explains what data is fetched, but lacks details on return format or structure. It's minimally viable for a read-only tool with zero inputs.

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 0 parameters, with 100% schema description coverage. The description doesn't need to explain parameters, and it appropriately focuses on the data retrieved. A baseline of 4 is applied for zero-parameter tools.

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 with specific resources: 'account health, credit status, pixel counts, and intent audience slot status.' It uses the verb 'Get' which matches the tool name, but it doesn't explicitly differentiate from sibling tools like 'get_audience_status' or 'get_audience_stats' that might overlap in 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context, or exclusions, leaving the agent to infer usage from the tool name and description 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?

The annotation 'readOnlyHint: true' already indicates this is a safe read operation. The description adds minimal behavioral context beyond that—it specifies retrieval by ID but doesn't disclose error handling (e.g., what happens if the ID is invalid), performance characteristics, or authentication requirements. With annotations covering the safety profile, the description meets baseline expectations without adding rich 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?

The description is a single, efficient sentence that front-loads the core action ('Get one saved audience by id'). There is no wasted verbiage, repetition, or unnecessary elaboration—every word contributes directly to understanding the tool's function.

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 (1 required parameter) and the annotation covering safety, the description is minimally adequate. However, with no output schema and incomplete parameter guidance (e.g., no error handling or ID sourcing), it leaves the agent to guess about return values and edge cases. It meets the baseline for a simple read tool but doesn't fully prepare the agent for robust 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?

The input schema has 1 parameter ('id' of type UUID) with 0% description coverage, so the schema provides no semantic context. The description compensates by specifying that 'id' refers to a saved audience, clarifying its purpose. However, it doesn't explain where to obtain this ID (e.g., from 'list_audiences') or format details beyond 'uuid' in the schema, leaving some gaps.

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 resource ('one saved audience by id'), making the purpose immediately understandable. It distinguishes from siblings like 'list_audiences' (which retrieves multiple) and 'get_audience_stats' (which provides analytics rather than the audience object itself). However, it doesn't explicitly mention what an 'audience' represents in this context (e.g., a marketing segment), which prevents a perfect 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing audience ID), contrast with 'list_audiences' for browsing, or specify use cases like retrieving details for editing or analysis. The agent must infer usage from the tool name and sibling names 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?

The annotations indicate readOnlyHint=true, which the description aligns with by using 'Get' (a read operation). The description adds context about the purpose ('for audience preview and query'), but doesn't disclose additional behavioral traits like rate limits, authentication needs, or response format. With annotations covering safety, this earns a baseline score for adding some value without contradictions.

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 directly states the tool's function without fluff. It's front-loaded with the core action and resource, making it easy to understand quickly. Every word earns its place, achieving optimal 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 the tool has no parameters, annotations for read-only safety, but no output schema, the description is adequate but minimal. It explains what the tool does but doesn't cover return values or detailed usage scenarios. For a simple read tool, this is the minimum viable, leaving gaps in contextual guidance.

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 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, which is appropriate. Baseline is 4 for zero parameters, as it avoids unnecessary repetition and focuses on the tool's purpose.

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 'available ICP filter values', specifying the purpose is to retrieve filter values for audience preview and query. It distinguishes from siblings like 'get_audience' or 'get_audience_stats' by focusing on filters rather than audience data or statistics. However, it doesn't explicitly differentiate from 'get_topic_facets' or similar filter-related tools, keeping it at a 4.

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. It mentions 'audience preview and query' as contexts, but doesn't specify prerequisites, exclusions, or compare to siblings like 'preview_audience' or 'query_audience'. This lack of explicit usage instructions results in a minimal score.

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?

Annotations provide readOnlyHint=true, indicating a safe read operation. The description adds context about pagination and date/latest-run scoping, which is useful behavioral detail beyond annotations. However, it doesn't mention rate limits, authentication needs, or response 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, efficient sentence with zero waste. It front-loads key information (paginated results, scope options) without unnecessary elaboration.

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 read-only tool with annotations covering safety, the description adds pagination and scope context, but lacks output details (no output schema) and leaves parameters mostly unexplained. Given 4 parameters with 0% schema coverage, it's incomplete but 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 description coverage is 0%, so the schema provides no parameter descriptions. The description mentions 'latest run or a specific date', hinting at 'date' parameter usage, but doesn't explain 'id' (required UUID), 'limit' (pagination size), or 'cursor' (pagination token). It fails to compensate for the low 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 resource 'paginated full audience results', specifying scope for 'latest run or a specific date'. It distinguishes from siblings like 'get_audience' (single audience) or 'list_audience_runs' (runs metadata), but could be more explicit about the distinction.

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 audience results with pagination, but doesn't explicitly state when to use this vs. alternatives like 'get_audience_stats' or 'export_audience'. No guidance on prerequisites or exclusions 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?

Annotations provide readOnlyHint=true, indicating a safe read operation. The description adds value by specifying the scope ('field fill rates for the latest run or a specific audience date'), which isn't covered by annotations. However, it lacks details on output format, error handling, or rate limits, leaving behavioral gaps despite the annotation support.

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 front-loads the core purpose ('Get field fill rates') and adds necessary scope details. There is no wasted wording, and it directly addresses the tool's function without redundancy.

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 moderate complexity (2 parameters, no output schema), the description covers the basic purpose and scope but lacks details on parameter meanings, output format, and usage context. With annotations providing safety info, it's minimally adequate but has clear gaps in guiding effective 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?

Schema description coverage is 0%, so the description must compensate for undocumented parameters. It mentions 'latest run or a specific audience date,' hinting at the 'date' parameter's purpose, but doesn't explain the 'id' parameter (required) or provide format details. This partial compensation is insufficient for full clarity, scoring below 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 action ('Get field fill rates') and resource ('audience'), specifying it's for 'the latest run or a specific audience date.' It distinguishes from siblings like 'get_audience' or 'get_audience_results' by focusing on statistical fill rates rather than general audience data or results. However, it doesn't explicitly contrast with all siblings, keeping it at a 4 rather than a 5.

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 minimal guidance, mentioning 'latest run or a specific audience date' but not clarifying when to use this versus alternatives like 'get_audience_results' or 'query_audience.' No explicit when-not-to-use advice or prerequisites are given, leaving the agent to infer usage from context 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?

Annotations provide readOnlyHint=true, indicating a safe read operation. The description adds context about retrieving 'current materialization status' and the option for latest run or specific date, which is useful beyond annotations. However, it doesn't disclose rate limits, error conditions, or response format details that would enhance behavioral understanding.

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 front-loads the purpose ('Get the current materialization status') and includes key options ('latest run or a specific date'). There is no wasted verbiage, 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?

Given no output schema and 0% schema description coverage, the description is incomplete. It covers the basic purpose and parameter intent but lacks details on return values, error handling, or deeper context about materialization processes. With annotations covering safety, it's minimally adequate but leaves gaps for effective tool 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?

Schema description coverage is 0%, so the description must compensate. It mentions 'latest run or a specific date', which loosely maps to parameters (id for run, date for date), but doesn't explain that 'id' is required and is a UUID, or that 'date' follows a specific pattern. The description adds minimal semantic value beyond the bare 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 ('Get') and resource ('Audience Status'), specifying it retrieves materialization status for either the latest run or a specific date. It distinguishes from siblings like 'get_audience' (general audience data) and 'get_audience_results' (results rather than status), but could be more explicit about the distinction.

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 checking materialization status, with an alternative between latest run or specific date. However, it lacks explicit guidance on when to use this versus siblings like 'get_audience' or 'list_audience_runs', and doesn't mention 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?

The annotations already declare readOnlyHint=true, indicating a safe read operation. The description adds minimal behavioral context by specifying what data is retrieved ('types, industries, and categories'), but does not disclose details like rate limits, authentication needs, or response format. With annotations covering safety, a baseline 3 is appropriate.

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 front-loads the key action ('Get available...') and resource. There is no wasted verbiage, making it highly concise and well-structured for quick understanding.

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 (0 parameters, read-only) and lack of an output schema, the description is minimally adequate. It states what data is fetched but does not explain the return format or usage context, leaving gaps that could hinder an agent's ability to use it effectively without trial.

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 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately does not discuss parameters, earning a high score as it avoids redundancy and focuses on the tool's purpose.

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 with specific verbs ('Get available types, industries, and categories') and identifies the resource ('topic discovery filters'). However, it does not explicitly differentiate from sibling tools like 'get_audience_filters' or 'list_topics', which reduces the score from a perfect 5.

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. It mentions 'topic discovery filters' but does not specify scenarios, prerequisites, or exclusions, nor does it reference sibling tools like 'search_topics' or 'list_topics' for 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?

The annotations include 'readOnlyHint: true', indicating this is a safe read operation. The description adds value by specifying the metric ('day-over-day audience growth or decline'), which isn't covered by annotations. However, it lacks details on behavioral traits like rate limits, data freshness, or output format, leaving gaps in understanding how the tool behaves beyond being read-only.

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: 'Get top topics by day-over-day audience growth or decline.' It's front-loaded with the core purpose, has zero wasted words, and is appropriately sized for the tool's complexity, making it easy to parse quickly.

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 complexity (4 parameters, no output schema, and annotations only covering read-only status), the description is incomplete. It doesn't explain parameters, output format, or key behavioral aspects like sorting or data scope. With low schema coverage and no output schema, the description should provide more context to help an agent use the tool effectively.

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 4 parameters with 0% description coverage, meaning no parameter details are documented in the schema. The description doesn't explain any parameters, such as what 'limit', 'direction', 'type', or 'industry' mean or how they affect the results. This fails to compensate for the low schema coverage, leaving parameters largely unexplained.

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: 'Get top topics by day-over-day audience growth or decline.' It specifies the verb ('Get'), resource ('top topics'), and key metric ('day-over-day audience growth or decline'), making the action distinct. However, it doesn't explicitly differentiate from sibling tools like 'get_topic_trend' or 'list_topics', which might also involve topic retrieval, so it doesn't fully earn a 5.

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. It doesn't mention sibling tools or contexts where other tools might be more appropriate, such as using 'get_topic_trend' for trend analysis or 'list_topics' for general listing. Without any usage context or exclusions, it offers minimal help 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?

Annotations indicate readOnlyHint=true, so the agent knows this is a safe read operation. The description adds context by specifying 'daily trend time series', which hints at temporal data retrieval, but doesn't disclose behavioral traits like rate limits, authentication needs, or output format. With annotations covering safety, a 3 is appropriate as the description adds some value but minimal behavioral 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 a single, efficient sentence with no wasted words, clearly front-loaded with the core action. It's appropriately sized for a simple tool, making it easy to parse quickly.

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 (1 parameter, no output schema) and annotations covering read-only safety, the description is minimally adequate. However, it lacks details on output format, error handling, or integration with siblings, leaving gaps in full contextual understanding for effective 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?

Schema description coverage is 0%, so the schema only defines 'topicId' as an integer >0 without descriptions. The description mentions 'for a single topic', which loosely relates to the parameter but doesn't add meaningful semantics like what a topicId represents or how to obtain it. Baseline 3 is applied as the description compensates slightly but inadequately for the coverage 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 verb 'Get' and the resource 'daily trend time series for a single topic', making the purpose specific and understandable. However, it doesn't explicitly distinguish this tool from siblings like 'get_topic_movers' or 'get_topic_facets', which might also retrieve topic-related data, leaving some ambiguity in 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, exclusions, or compare it to sibling tools like 'compare_topics' or 'search_topics', leaving the agent to infer usage based on 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?

Annotations provide readOnlyHint=true, indicating a safe read operation, which the description does not contradict. The description adds context by specifying 'daily runs,' which hints at temporal scope, but it lacks details on behavior like pagination, rate limits, or response format. With annotations covering safety, the description adds some value but not rich 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 front-loads the core action ('List available daily runs') without unnecessary words. It earns its place by clearly stating the purpose, making it appropriately sized 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 the tool has one parameter, annotations for safety, and no output schema, the description is minimally adequate. It covers the basic purpose but lacks details on output (e.g., what data 'daily runs' include), usage context, or error handling, leaving room for improvement in 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?

The input schema has one parameter ('id') with 0% description coverage, so the schema provides no semantic information. The description compensates by implying the 'id' refers to a 'saved audience,' adding meaningful context beyond the schema. However, it does not specify the format or source of the ID, leaving minor gaps.

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 ('available daily runs for a saved audience'), making the purpose specific and understandable. However, it does not explicitly differentiate from sibling tools like 'list_audiences' or 'get_audience_results', which might also involve listing audience-related data, so it lacks sibling 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?

The description provides no guidance on when to use this tool versus alternatives, such as 'list_audiences' for general audience lists or 'get_audience_results' for specific run results. It mentions 'saved audience' but does not clarify prerequisites or exclusions, leaving usage context implied at best.

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 annotation 'readOnlyHint: true' already indicates this is a safe read operation. The description adds minimal behavioral context by specifying 'saved audiences' (implying persistent data) and 'authenticated organization' (implying scope), but doesn't detail return format, pagination, or error handling. With annotations covering safety, this meets the baseline for adding some value without contradiction.

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 front-loads the core purpose ('List saved audiences') and adds necessary scope ('for the authenticated organization'). Every word earns its place with zero waste, 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?

Given the tool's simplicity (0 parameters, read-only annotation, no output schema), the description is adequate but minimal. It covers the basic what and scope, but lacks details on output (e.g., list format, fields) or usage context relative to siblings. For a list operation in a rich sibling set, more guidance 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 0 parameters and 100% schema description coverage, the schema fully documents the lack of inputs. The description doesn't need to compensate for any gaps, as there are no parameters to explain. It appropriately focuses on the tool's purpose without redundant parameter details.

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 resource ('saved audiences'), with the scope ('for the authenticated organization') providing useful context. However, it doesn't explicitly differentiate from sibling tools like 'get_audience' or 'list_audience_runs', which would require more specific language about what 'list' entails versus 'get' or 'list runs'.

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 like 'get_audience' (for a specific audience) or 'list_audience_runs' (for runs of audiences). It lacks explicit when/when-not instructions or named alternatives, leaving the agent to infer usage from tool names 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?

Annotations already declare readOnlyHint=true, indicating a safe read operation. The description adds that it lists 'all' tracking pixels for the organization, implying no filtering parameters, which is useful context beyond annotations. However, it doesn't disclose behavioral aspects like pagination, rate limits, or what 'all' entails (e.g., active only, includes deleted).

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 directly states the tool's purpose without unnecessary words. It is front-loaded with the core action and resource, making it easy to parse. Every part of the 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 low complexity (0 parameters, read-only per annotations) and no output schema, the description is minimally adequate. It covers the basic purpose but lacks details on output format, error handling, or organizational context that could help an agent use it effectively. It meets the minimum viable threshold but has clear 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?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description implicitly confirms there are no filtering options by stating 'List all', which aligns with the empty schema. This provides adequate semantic context for a parameterless tool.

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 ('tracking pixels'), specifying scope for 'the authenticated organization'. It distinguishes from siblings like 'create_pixel' or 'update_pixel', but doesn't explicitly differentiate from other list tools like 'list_audiences' or 'list_topics' in terms of what makes tracking pixels unique.

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. It doesn't mention prerequisites, timing considerations, or compare with other list operations (e.g., 'list_audiences' for audiences vs. 'list_pixels' for pixels). The description is purely declarative without 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?

Annotations provide readOnlyHint=true, indicating this is a safe read operation. The description adds value by specifying the filtering capabilities (type, industry, category, text query), which gives context beyond the annotations. However, it doesn't disclose behavioral traits like pagination, rate limits, or response format, which would be helpful given no output 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, efficient sentence that front-loads the purpose and key features. Every word earns its place with no redundancy or waste, making it highly concise and well-structured for quick understanding.

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 moderate complexity (4 parameters, no output schema, read-only annotation), the description is minimally adequate. It covers the purpose and filtering options but lacks details on output format, error handling, or sibling differentiation, leaving gaps that could hinder effective agent 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?

Schema description coverage is 0%, so the description must compensate. It lists the filterable fields (type, industry, category, text query), which maps to the 4 parameters, but doesn't explain their semantics, such as what 'type' values mean or how 'q' differs from other filters. This adds some meaning but insufficiently compensates for the lack of 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 clearly states the action ('Browse') and resource ('Leadpipe intent topics'), making the purpose evident. It distinguishes from some siblings like 'analyze_website_topics' or 'search_topics' by focusing on browsing with filters, but could be more explicit about how it differs from 'search_topics' specifically.

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 filtering capabilities but provides no guidance on when to use this tool versus alternatives like 'search_topics' or 'get_topic_facets'. It lacks explicit when/when-not instructions or named alternatives, leaving usage context implied rather than clearly defined.

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 annotation 'readOnlyHint: true' already indicates this is a safe read operation. The description adds value by specifying what gets previewed (size and masked sample rows) and the purpose (before loading full results), but doesn't disclose additional behavioral traits like rate limits, authentication needs, or what 'masked' entails. No contradiction with annotations exists.

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

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

The description is a single, efficient sentence that front-loads the core purpose. Every word earns its place, with no redundancy or fluff, making it easy to parse quickly.

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 (5 parameters with nested objects, no output schema), the description is incomplete. It adequately covers the purpose and context but lacks details on parameters, return values, and behavioral nuances. The annotation helps with safety, but more is needed for a tool with this parameter richness.

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 and 5 parameters (including a complex nested 'filters' object), the description provides no parameter information beyond what's implied by the tool name. It doesn't explain what 'topicIds', 'minScore', or other parameters mean, failing to 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 specific action ('preview audience size and masked sample rows') and distinguishes it from sibling tools like 'create_audience', 'export_audience', or 'get_audience_results' by emphasizing it's a preview before loading full results. It uses precise verbs ('preview') and specifies the resource ('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 context ('before loading full results'), suggesting this tool is for preliminary assessment. However, it doesn't explicitly state when to use alternatives like 'create_audience' or 'export_audience', nor does it mention prerequisites or exclusions, leaving some guidance gaps.

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 annotation 'readOnlyHint: true' already indicates this is a safe read operation. The description adds some context by specifying it uses a 'public query endpoint', which implies accessibility but doesn't elaborate on rate limits, authentication needs, or what 'browse' entails. It doesn't contradict annotations, but provides only modest additional 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?

The description is a single, efficient sentence that gets straight to the point without unnecessary words. It's appropriately sized for a tool with many parameters, though it could benefit from slightly more detail to justify its brevity given the complexity.

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 9 parameters, 0% schema description coverage, no output schema, and complex nested objects, the description is inadequate. It lacks parameter explanations, usage context, and output details, making it incomplete for effective agent use despite the readOnlyHint annotation providing some safety 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?

With 0% schema description coverage and 9 parameters (including complex nested objects), the description fails to explain any parameters. It doesn't clarify what 'audienceId', 'topicIds', 'filters', or other inputs mean, leaving the agent reliant solely on schema structure without semantic guidance, which is insufficient given the low 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 ('Run an ad hoc audience query or browse a saved audience run') and resource ('via the public query endpoint'), making the purpose understandable. However, it doesn't explicitly differentiate this tool from sibling tools like 'get_audience_results' or 'preview_audience', which might have overlapping functionality, preventing a perfect 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?

The description provides minimal guidance by mentioning 'ad hoc' vs 'saved audience run', but offers no explicit advice on when to use this tool versus alternatives like 'get_audience_results' or 'preview_audience'. There's no mention of prerequisites, performance considerations, or specific scenarios where this tool is preferred over others.

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 annotation 'readOnlyHint: true' already indicates this is a safe read operation. The description adds some context about what type of data is returned ('resolved visitor data' and 'visitor journey'), but doesn't disclose important behavioral traits like pagination behavior, rate limits, authentication requirements, or what 'resolved' specifically means. No contradiction with annotations exists.

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

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

The description is extremely concise with just two sentences that are front-loaded with essential information. Every word earns its place, with no wasted text or redundancy.

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 parameters with 0% schema coverage and no output schema, the description is incomplete. While it provides basic usage patterns, it lacks details on return values, error conditions, and full parameter semantics. The annotations help with safety context, but more behavioral information would be needed for 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?

With 0% schema description coverage, the description carries full burden for explaining parameters. It mentions email, timeframe, domain, and page filters, giving basic semantic context, but doesn't explain what 'page' refers to (likely pagination), what 'domain' filtering entails, or the meaning of 'resolved' in the context. This leaves significant gaps in parameter understanding.

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 'query' and resource 'resolved visitor data', making the purpose understandable. However, it doesn't explicitly differentiate this tool from sibling tools like 'query_audience' or 'get_audience_results', which appear to be related to audience data rather than visitor journeys.

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 on when to use different parameter combinations: 'Pass email for a single visitor journey, or use timeframe/domain/page filters for broader results.' This gives practical guidance, though it doesn't explicitly state when NOT to use this tool or name specific alternatives among the 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?

The annotation 'readOnlyHint: true' already indicates this is a safe read operation. The description adds some behavioral context by specifying the search is 'by name' and for 'autocomplete or discovery', but doesn't disclose additional traits like rate limits, authentication needs, or result format. No contradiction with annotations exists.

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

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

The description is a single, efficient sentence with zero waste. It's front-loaded with the core purpose and includes only essential context. Every word earns its place without redundancy or 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?

Given 4 parameters with 0% schema coverage, no output schema, and only a basic read annotation, the description is incomplete. It fails to explain parameter meanings or behavioral details like result structure, making it inadequate for an agent to use the tool effectively without guessing.

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 for undocumented parameters. It only mentions searching 'by name', which relates to the 'q' parameter, but doesn't explain the semantics of 'industry', 'type', or 'limit'. This leaves three parameters without meaningful context 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 purpose as searching intent topics by name, specifying it's for autocomplete or discovery. It uses specific verbs ('search') and identifies the resource ('intent topics'), but doesn't explicitly differentiate from sibling tools like 'list_topics' or 'get_topic_facets' which might have overlapping functionality.

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 minimal guidance by mentioning 'autocomplete or discovery' contexts, but offers no explicit when-to-use rules, no exclusions, and no comparison to alternatives like 'list_topics' or 'get_topic_facets' from the sibling list. The agent must infer usage from the purpose 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions updating and status changes, but lacks critical details such as required permissions, whether updates are reversible, rate limits, or what happens to unspecified fields. This is inadequate for a mutation tool with complex parameters.

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 with zero waste. It's front-loaded with the core action and includes a useful detail about status changes, making it appropriately sized for its 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 tool's complexity (5 parameters, nested objects, no output schema, and no annotations), the description is insufficient. It doesn't explain the update scope, return values, error conditions, or how it differs from siblings, leaving significant 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 0%, so the description must compensate for undocumented parameters. It only hints at 'activating or pausing' (related to the 'status' parameter) but ignores the other 4 parameters (id, name, config, audienceSize) and nested structures. This adds minimal 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 verb ('update') and resource ('saved audience'), making the purpose evident. It also specifies what can be updated ('activating or pausing it'), which adds specificity. However, it doesn't explicitly differentiate from sibling tools like 'create_audience' or 'delete_audience' beyond the verb itself.

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. It doesn't mention prerequisites (e.g., needing an existing audience ID), exclusions (e.g., what can't be updated), or comparisons to siblings like 'create_audience' for new audiences or 'delete_audience' for removal.

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 for behavioral disclosure. While it mentions the three operations (pause, activate, update excluded paths), it doesn't describe what happens during these operations, whether they're reversible, what permissions are required, or what the response looks like. For a mutation tool with zero annotation coverage, this is insufficient.

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 - a single sentence that efficiently communicates the core functionality without any wasted words. It's front-loaded with the essential information and has perfect structure 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?

For a mutation tool with 3 parameters, 0% schema description coverage, no annotations, and no output schema, the description is incomplete. It doesn't explain the impact of operations, error conditions, or provide enough context for an agent to use it effectively without additional 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?

The description mentions 'excluded paths' which maps to one parameter, but with 0% schema description coverage and 3 total parameters, it doesn't adequately explain what 'id' represents or the significance of the 'status' enum values. The description adds minimal value beyond what the schema structure implies.

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 with specific verbs (pause, activate, update) and resource (pixel), making it easy to understand what the tool does. However, it doesn't explicitly differentiate this from sibling tools like 'create_pixel' or 'list_pixels', which would be helpful for agent selection.

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. There are multiple sibling tools related to pixels and audiences, but no indication of prerequisites, when this tool is appropriate, or what distinguishes it from 'update_audience' or other modification tools.

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