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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It does not mention whether the operation is read-only, what the output looks like, how breakdown works, rate limits, or authentication needs. The only hint is that it 'compares performance,' which is too vague for a tool with 7 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, concise sentence with no wasted words. However, it is under-specified and lacks any structured breakdown of behavior or parameters. While conciseness is acceptable, the structure is minimal and does not earn the score higher than mid-range.

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 7 parameters, an output schema, and no annotations, this description is severely incomplete. It fails to explain the tool's purpose beyond a vague 'compare performance,' doesn't describe the period parameters, doesn't mention the breakdown option, and offers no context on when to use it. The tool needs much more elaboration to be usable.

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 43%, meaning only 3 of 7 parameters have descriptions in the schema. The tool description adds no information about any parameters, let alone the date ranges or breakdown field. It fails to compensate for the low schema coverage, leaving users without guidance on date formats, required fields, or how the breakdown parameter affects results.

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: comparing performance between two date ranges. It uses a specific verb ('compare') and resource ('performance'), and the comparison aspect distinguishes it from sibling tools that retrieve performance for a single period. However, it doesn't specify what kind of performance metrics or the output format, so it's not fully detailed.

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 is given about when to use this tool versus alternatives like get_campaign_performance or get_account_summary. The name and description imply its use for comparing two periods, but there are no stated exclusions, prerequisites, or alternative tool recommendations.

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 for behavioral transparency. It only states the basic read action ('Get') without disclosing any side effects, prerequisites, rate limits, or limitations such as data freshness 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, well-structured sentence that front-loads the core action and result. There is no filler or redundancy, making it highly efficient.

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

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

Despite having an output schema and full parameter coverage, the description lacks contextual details such as aggregation scope, how 'top-level' relates to account hierarchy, and when to prefer this over sibling reporting tools. This makes it minimally complete for an agent to select and invoke correctly.

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

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

The input schema fully documents all four parameters with types, formats, and defaults, achieving 100% coverage. The description adds no extra meaning beyond the schema, so the baseline score of 3 is appropriate.

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

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

The description clearly states that the tool retrieves account-level spend and conversion totals. This distinguishes it from sibling tools that focus on campaigns, keywords, ads, or search terms, 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?

The description provides no guidance on when to use this tool versus alternatives like get_campaign_performance or compare_periods. It lacks any explicit context, exclusions, or alternative recommendations, leaving the agent to infer usage 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?

No annotations are provided, so the description must disclose behavioral expectations. It only states the operation and metric names; it does not mention data freshness, sorting, row limits, filtering behavior, or any side effects/requirements beyond the operation name.

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

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

The description is a single, focused sentence that front-loads the core purpose and lists key result dimensions. 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?

An output schema is present, so return values don't need description. However, the tool has six parameters with three required but no guidance on required inputs or how to combine filters; the description is adequate for a simple read but leaves contextual 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 description does not explain any parameters. The schema covers some parameters (customer_id, campaign_id, row_limit) but leaves start_date, end_date, and account undescribed; the description does not compensate or clarify date formats or account 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 clearly states the tool retrieves ad-level performance and specifies the metrics included (headlines, descriptions, CTR, conversions), distinguishing it from sibling campaign- and keyword-level tools.

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

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

The description implies it should be used when ad-level metrics are needed, but it does not explicitly compare to alternatives like get_campaign_performance or get_keyword_performance, nor state when not to use it.

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

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

No annotations are provided, so the description should carry the burden. The description only states what it does ('Get') but doesn't disclose any behavioral traits such as data aggregation, timezone handling, pagination, or potential side effects. It implies a read-only operation, but lacks depth.

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

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

The description is a single clear sentence with no fluff, front-loading the main action. However, it is somewhat minimal and omits useful context that could be added without sacrificing 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?

The tool has multiple parameters, sibling tools, and an output schema (though not shown). The description gives only the basic purpose and misses usage guidance, behavioral transparency, and parameter nuances. It feels incomplete for effective selection and invocation.

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

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

Schema description coverage is 100%, with each parameter well-documented. The description adds no additional parameter semantics beyond the schema, so the baseline of 3 is appropriate.

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

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

The description uses a specific verb ('Get') and identifies the resource ('campaign performance metrics') and scope ('date range'). It clearly states the tool's function, though it doesn't explicitly differentiate from sibling metrics tools like get_ad_performance or get_keyword_performance, which are distinct but similar.

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 that this is for campaign-level performance, nor does it compare with sibling tools. Users must infer context from the tool name and sibling list.

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

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It only states the output (keyword performance, quality scores) but offers no details on read-only nature, pagination, date range handling, filtering, or potential side effects. 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 concise sentence that front-loads the core purpose. No unnecessary words or repetition, making it efficient and to the point.

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

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

Given the presence of an output schema and the fact that parameter semantics are covered by the schema, the description sufficiently communicates the tool's core function. However, it could benefit from mentioning optional filtering capabilities or the meaning of 'performance' metrics, which would improve completeness for users needing to select between sibling tools.

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

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

The description adds no parameter-specific information, but the schema provides descriptions for 4 of 6 parameters (67% coverage), including row_limit, campaign_id, customer_id, and account. The missing descriptions for start_date and end_date are self-explanatory given their names, so the schema largely carries the semantic weight.

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 'Get keyword-level performance including quality scores' clearly specifies the verb and resource, and explicitly identifies the granularity as keyword-level, distinguishing it from sibling tools like get_campaign_performance and get_ad_performance.

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 keyword-level performance but does not explicitly state when to use this tool over siblings or mention any exclusions or prerequisites. It's not misleading, but 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 are provided, so the description must fully disclose behavioral traits. It only states the listing action and default account, with no mention of side effects, read-only nature, permissions, or response characteristics. The tool's behavior is largely transparent (non-destructive), but the description does not state this, so it fails to disclose anything 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?

The description is a single, focused sentence that states the tool's purpose and additional relevant detail (default account). It is concise, well-structured, and every word contributes meaning without 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 the tool's simplicity (no parameters, output schema exists), the description covers the basic purpose. However, it lacks behavioral context (e.g., read-only nature) and does not position the tool among its siblings, leaving some gaps in guidance for agents. It is minimally sufficient for a simple tool but not richly 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?

With zero parameters, the schema already fully describes the input requirements. The description does not need to explain parameter semantics, and the baseline of 4 applies. The description does not add anything about parameters, but none are needed.

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

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

The description uses a specific verb ('List') and a clear resource ('all configured Google Ads accounts'), and adds unique information about the current default account. However, it does not explicitly differentiate from sibling tools like list_customers, though the term 'configured accounts' is somewhat distinct.

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_customers or set_default_account. There is no mention of context, prerequisites, or exclusions, leaving the agent without information for tool 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?

There are no annotations, so the description must carry the transparency burden. It only states the basic action and does not disclose behaviors such as default status filtering (ENABLED and PAUSED), whether it is read-only, pagination, or any effects. This leaves the agent to infer important operational 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, concise sentence with no fluff. It is appropriately front-loaded, though it is so brief that it lacks informative substance. Still, it does not waste 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 the context signals (3 params, no annotations, many siblings), the description is too sparse. It does not mention the default status behavior, how results are returned, or when to prefer this over related tools. The output schema exists but the description still fails to frame the tool's role.

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

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

The input schema has 100% description coverage for all three parameters, including the default for 'status'. The description adds no additional semantics beyond the schema, so the baseline of 3 is appropriate.

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

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

The description uses a specific verb 'List' with a clear resource 'campaigns' and a context 'for an account'. This is unambiguous, but it does not differentiate from sibling tools like get_campaign_performance or get_account_summary, which may also operate on 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 vs alternatives. Sibling tools like get_campaign_performance and compare_periods exist, but the description offers no exclusions or contextual hints about which tool to choose.

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 carry the transparency burden. It reveals meaningful behavior: the conditional listing based on customer_id and the scope of 'accessible' accounts. However, it lacks details on authentication, pagination, or the meaning of the 'account' parameter, leaving some behavioral aspects undisclosed.

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

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

The description is two sentences long, front-loaded with the core purpose, and adds conditional details without redundant information. Every word serves a purpose.

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

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

The description covers the main functionality and the customer_id behavior clearly. However, the 'account' parameter is ambiguous, and the relationship to sibling tools is not addressed. Given the output schema exists, return values are covered, but the parameter ambiguity prevents a higher score.

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 provides no parameter descriptions, and the description only explains customer_id ('If customer_id is provided, lists child accounts under that MCC'). The 'account' parameter is left entirely unexplained, which is a significant gap given the 0% schema coverage. The description does not fully compensate for the missing schema 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 tool's purpose: 'List all accessible Google Ads customer accounts.' It also explains the conditional behavior based on customer_id, listing child accounts under an MCC when provided, which distinguishes it from sibling tools like list_accounts.

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 the tool (to list customer accounts) and how to use the optional customer_id parameter, but it does not mention alternatives or when not to use it. With sibling list_accounts present, explicit differentiation would improve the 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?

No annotations are present, so the description carries the full transparency burden. It states a read-like action ('Get') but does not disclose limitations, data freshness, or whether results are historical or real-time. The row_limit and default are only in the schema, not 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 a single 10-word sentence with no filler. It delivers the core message immediately and is appropriately terse for a simple reporting tool.

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 having an output schema, the description is incomplete for a tool with 3 required parameters and optional filters. It leaves out any discussion of date ranges, filtering, or typical use cases. The absence of sibling differentiation further reduces its completeness for an agent's decision-making.

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

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

The description adds no information about parameters beyond what the schema already provides. It does not clarify the date format or the meaning of start_date/end_date, which are undocumented in the schema. The only parameter-related insight, 'your ads,' is too vague to be useful.

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 'Get actual search terms that triggered your ads' uses a clear verb and resource. It explicitly says 'actual search terms' which differentiates it from sibling tools like get_keyword_performance or get_ad_performance, making the tool's 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?

The description does not mention when to use this tool vs alternatives such as get_keyword_performance or get_ad_performance. There is no 'use this when' or 'instead of' language. The agent is left to infer that this tool is for search-term (query) reporting, but no explicit 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 carries the full burden of behavioral disclosure. It states the immediate effect (setting the default account) but omits critical details such as persistence, scope (session vs global), validation of the account, and whether prior defaults are overwritten. This is a meaningful gap 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, focused sentence with no superfluous words. It front-loads the verb and resource, making it immediately understandable. Perfect 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?

The description covers the basic purpose but lacks workflow context, such as referencing list_accounts to select a valid account, or clarifying whether the default persists across sessions. Given the tool's simplicity and the presence of an output schema, it is minimally adequate but leaves operational questions unanswered.

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 provides no additional meaning for the 'account' parameter. It does not specify whether the account is an ID, name, or email, nor how to discover valid values (e.g., via list_accounts). The parameter remains ambiguous.

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: 'Set the default account used when no account is specified in other tools.' It uses a specific verb ('Set') and resource ('default account'), and explicitly distinguishes it from sibling tools by explaining its role as a global setting affecting other 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 clear context on when to use the tool—when a default account is needed for other tools. It does not explicitly mention alternatives or exclusions, but the purpose is unambiguous and sufficient for a simple setter, earning a 4.

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