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

With no annotations provided, the description carries the full disclosure burden, yet it only implies read-only behavior via the verb 'List' without confirming it. It does not mention Google Ads authentication/scopes, pagination, depth limits on nesting, or error cases — significant gaps for an API-backed 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 purpose is front-loaded in a single clear sentence and the parameter note is compact. The 'Args:' docstring-style formatting is slightly unusual for an MCP definition but adds no real bloat.

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

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

For a single-parameter tool with an output schema present, coverage is mostly adequate: purpose and the input format are covered, and return values can live in the output schema. Still, with no annotations, the missing authentication and read-only confirmation leave the picture incomplete for an external API call.

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

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

Schema coverage is 0%, so the description must compensate, and it does: 'The manager account's customer ID (10 digits, dashes optional)' adds format, length, and meaning that the bare string schema lacks. Could go further (e.g., validation behavior), but this is strong compensating detail.

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?

States a specific verb and resource: 'List the accounts under a Google Ads manager (MCC) account', and adds a useful detail ('including nesting level'). It conceptually separates from the sibling list_accessible_customers, but does not explicitly name or contrast the sibling, so it stops short of 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?

Provides no guidance on when to use this tool vs alternatives such as list_accessible_customers or run_gaql. There is no mention of exclusions, prerequisites, or situations where a sibling is preferable, so the agent must infer the choice on its own.

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 does not mention read-only behavior, authentication requirements, pagination, rate limits, or any side effects. Although 'get' implies a read operation, the description offers no explicit behavioral context beyond its purpose.

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

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

The description is concise: one sentence for purpose followed by a compact argument list. Every line adds value, and the purpose is front-loaded. No fluff 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?

The description covers all parameters and the core purpose, and the output schema supplies return details. It is functionally complete for invocation. A minor gap is the lack of explicit usage guidance relative to siblings, but that is covered under usage_guidelines; overall completeness is high.

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 zero description coverage, so the description must compensate, and it does thoroughly. It explains customer_id format (10 digits, dashes optional), date_range as a GAQL literal with examples, and campaign_id as an optional filter. This adds meaning well beyond the bare schema properties.

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 a specific verb (Get) and resource (ad group-level performance metrics), listing the exact metrics (impressions, clicks, cost, conversions). This clearly distinguishes it from sibling tools like get_campaign_performance and get_keyword_performance by the aggregation level.

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 explicitly state when to use this tool versus its alternatives. The purpose implies 'use for ad group metrics', but there is no mention of exclusions or conditions (e.g., 'for campaign-level metrics use get_campaign_performance'). The usage context is inferred rather than stated.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The verb 'get' implies a read operation, but the description does not explicitly state that it is non-mutating, requires authentication, or has rate limits. It also does not disclose whether results are paginated or if there are any side effects. For a read-only retrieval tool with no annotations, 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 concise: a single purpose line followed by a structured Args block. Every sentence earns its place—the purpose line states the outcome and metrics, and the Args block documents each parameter without fluff. It front-loads the core purpose and does not waste words on narratives. This is exemplary structure for a tool description.

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 relative simplicity (three parameters, one required) and the presence of an output schema (which presumably defines the return structure), the description covers the essential invocation details: parameter formats, defaults, and optionality. It does not mention any limitations like account access scope or timezone handling, but these are likely inferable from the context or covered by the output schema. The description is complete enough for an agent to call the tool correctly, though it lacks explicit edge-case warnings that would push it to a 5.

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 provides only titles and types with no descriptions (schema description coverage is 0%). The description's Args block fully compensates by explaining each parameter: customer_id is a 10-digit Google Ads ID with optional dashes, date_range is a GAQL literal with examples (LAST_30_DAYS, LAST_7_DAYS, THIS_MONTH), and campaign_id is optional and restricts to a single campaign. This adds substantial meaning beyond the schema and clarifies format and optionality.

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 opens with a clear verb and resource: 'Get campaign-level performance metrics' and names the specific metrics (impressions, clicks, cost, conversions). This distinguishes it from siblings like get_ad_group_performance and get_keyword_performance, which target different granularities, and from run_gaql which is a generic query tool. The agent can immediately tell what this tool does.

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 through its phrasing ('campaign-level') but does not explicitly state when to choose this over alternatives or when not to use it. There is no mention of 'use this for campaign metrics, use get_ad_group_performance for ad group metrics' or any exclusions. The optional campaign_id parameter hints at single-campaign filtering, but no guidance on when that is appropriate. This falls under 'implied usage' without clear 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, the description must disclose side effects and operational behavior. It lists return metrics but omits any mention of read-only guarantees, pagination, rate limits, or failure modes. For a read-oriented reporting tool, the absence of such context is a 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 front-loaded with the purpose in a single sentence, then provides a compact, well-formatted argument list. No fluff; each 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?

With an output schema available and all parameters documented, the description covers what an agent needs to call the tool correctly. It lacks explicit behavioral caveats (e.g., pagination), but these are partially mitigated by the output schema and the simplicity of the tool. Slightly incomplete on side effects, hence a 4.

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

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

Schema coverage is 0%, so the description fully compensates by explaining each parameter with examples and constraints: customer_id format (10 digits, dashes optional), date_range syntax (GAQL literals with examples), and campaign_id's optional restriction role. This adds meaning far 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 'Get keyword-level performance metrics' with a specific verb and resource, and enumerates the metrics (impressions, clicks, cost, conversions). This immediately distinguishes it from sibling tools like get_campaign_performance and get_ad_group_performance, which target different hierarchical levels.

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

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

The description implies its use for keyword-level metrics but does not explicitly contrast with alternatives such as run_gaql or get_ad_group_performance. It mentions an optional campaign_id but gives no when-to-use guidance versus other reporting tools, leaving the agent to infer appropriateness.

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

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It communicates that this is a read-only listing operation and adds a key nuance: it only lists directly accessible customer IDs, implying it does not include accounts accessible via hierarchy. However, it does not disclose return format, pagination, or any other behavioral details 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, well-constructed sentence with zero redundancy. It is front-loaded with the verb and resource, and the scoping qualifier 'directly accessible to the configured credentials' is concise and valuable. Every word earns its place.

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

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

Given the tool has no parameters and an output schema exists (as indicated by context signals), the description provides sufficient information for an agent to invoke the tool correctly. The note about 'directly accessible' is important for distinguishing it from hierarchy-aware tools. However, slightly more detail about what this tool returns (e.g., a list of IDs) would have been marginally more complete, though the output schema likely covers that.

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

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

The tool has no parameters, and schema description coverage is effectively 100% (trivially). Per the baseline rule for tools with zero params, a score of 4 is appropriate. The description correctly adds no unnecessary parameter information, since there are none.

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 a specific action ('List') and a specific resource ('Google Ads customer IDs') with a scope ('directly accessible to the configured credentials'). It distinguishes itself from siblings like get_account_hierarchy and list_campaigns by focusing solely on customer IDs rather than campaigns or performance data.

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 explicitly mention when to use this tool versus alternatives, nor does it state exclusions. However, the purpose is so specific and distinct from sibling tools that a competent agent can infer when to use it. Still, there is no direct guidance on when not to use it, which would be stronger.

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, and it does clarify the one important boundary: this returns settings, not metrics. However, it does not disclose pagination, quotas, or that customer_id must reference an accessible Google Ads account. Acceptable but not rich for a listing 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?

Purpose sentence is front-loaded, followed by a compact two-line arg block. Zero fluff, and every line adds value. Slightly more could be said about pagination but the size is appropriate for a simple two-parameter list 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?

Low-complexity tool with an output schema present (so return values needn't be explained) and both parameters fully documented. The main gaps are unaddressed pagination/limits and lack of explicit sibling routing, but none are critical given the simple surface area and existing output schema.

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

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

Schema description coverage is 0%, so both parameters are undocumented in the schema. The description fully compensates: it gives customer_id format guidance ('10 digits, dashes optional') and enumerates status's only valid values (ENABLED, PAUSED, REMOVED), which the schema lacks as enums. Complete compensation 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?

States a specific verb+resource+scope: 'List campaigns in an account with their basic settings.' The parenthetical 'no performance metrics' differentiates it from the performance-focused siblings (get_campaign_performance, get_ad_group_performance, get_keyword_performance). It stops short of naming the sibling explicitly, but the boundary is clear enough.

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 'no performance metrics' qualifier implies the user should turn to a performance tool when metrics are needed, but it never names an alternative such as get_campaign_performance, nor does it route to list_accessible_customers for discovering valid customer IDs. Usage context is implied rather than stated.

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

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

With no annotations, the description carries the full burden. It explicitly discloses that the tool is read-only ('cannot modify any Google Ads data') and that GAQL only supports SELECT, which is key behavioral context. It also provides a concrete query example. It does not mention pagination, rate limits, or error handling, but since an output schema exists and the tool is a raw query runner, these are less critical. The transparency is high, though not exhaustive.

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

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

The description is concise, front-loaded with the purpose and usage guidance, and organized with an Args section that cleanly lists parameters. Every sentence earns its place: the intro defines the tool, the second sentence gives usage context, and the args section covers both parameters. No 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?

For a raw query tool with only two parameters, a clear read-only guarantee, and an existing output schema, the description is complete. It gives the exact fallback use case ('not covered by other tools'), parameter formats, and a query example. The presence of an output schema obviates the need to describe return values. Nothing essential is missing for correct 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 0%, so the description must explain both parameters. It does so effectively: customer_id is described as 'Google Ads customer ID (10 digits, dashes optional)' and query as 'A GAQL SELECT query' with a representative example. This adds substantial meaning beyond the bare schema properties (which have no descriptions), fully compensating 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 tool 'runs a raw read-only GAQL SELECT query against the Google Ads API', naming a specific verb (run), resource (GAQL query), and its read-only nature. It explicitly differentiates from siblings by stating it is for reporting needs 'not covered by the other tools', making its purpose unambiguous and distinct from the other reporting 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 explicitly states when to use this tool: 'for reporting needs not covered by the other tools', and clarifies that GAQL only supports SELECT, so it cannot modify data. This gives clear usage context and implicitly tells the agent to prefer sibling reporting tools when they fit, reserving this for raw queries. No exclusions are needed beyond that.

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