Server Quality Checklist

Tool Scores

• get_advertiser_adsA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds the return content (headlines, descriptions, etc.) which is useful but not critical beyond annotations. No contradictions.

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

  Conciseness5/5

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

  The description is concise: two paragraphs, front-loaded with purpose, and bullet points for use cases. Every sentence adds value without redundancy.

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

  Completeness5/5

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

  With no output schema, the description adequately explains return values ('ad creatives with headlines, descriptions, thumbnails, and run dates'). Combined with full parameter documentation and annotations, it is complete for this straightforward list tool.

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

  Parameters3/5

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

  Schema description coverage is 100%, with all parameters documented in the schema. The description adds no additional parameter details, so baseline score 3 applies.

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

  Purpose5/5

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

  The description clearly states 'Retrieve all ads currently running for a specific advertiser', using a specific verb and resource. It distinguishes itself from sibling tools like compare_ad_presence, get_ad_details, etc., by focusing on listing ads for one advertiser.

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

  Usage Guidelines4/5

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

  The description provides explicit use cases (analyze competitors, see ad types, research ad copy, track activity), offering clear context for when to use the tool. It does not explicitly mention when not to use or compare with alternatives, but the context is sufficient.

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

• compare_ad_presenceA
  4.2/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true and idempotentHint=true, so the description's safety implications are already covered. The description adds value by specifying the return data (ad counts and format distribution per region), which goes beyond the annotations and helps the agent understand expected output.

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

  Conciseness5/5

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

  The description is remarkably concise: a single introductory sentence, a bulleted list of use cases, and a closing sentence about return values. Every sentence adds value, with no redundancy or filler.

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

  Completeness4/5

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

  The tool has 2 required parameters and no output schema, but the description explains the return format (ad counts and format distribution per region). While the exact structure is unspecified, the description provides sufficient context for a simple comparison tool, and annotations (readOnlyHint, idempotentHint) further inform behavior.

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

  Parameters3/5

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

  Schema description coverage is 100%, so both 'advertiserId' and 'regions' are already well-documented in the input schema. The description mentions 'regions' but does not add new semantic details beyond what the schema provides (e.g., maxItems constraint is already present).

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

  Purpose5/5

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

  The description clearly states the tool compares ad presence across multiple geographic regions, with a specific verb ('Compare') and resource ('ad presence'). It lists concrete use cases that distinguish it from sibling tools like get_ad_details or search_advertiser, which are not comparative.

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

  Usage Guidelines4/5

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

  The description provides explicit 'Use this tool to:' bullet points outlining contexts for use (e.g., competitor activity, market identification). It does not explicitly mention when not to use or alternative tools, but the listed scenarios are clear and differentiated from siblings.

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

• get_ad_detailsA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is clear. The description adds context such as targeting info being 'when available' and impression/spend ranges specific to political ads, which is useful beyond the annotations.

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

  Conciseness5/5

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

  The description is concise with a front-loaded main purpose and a bullet-like list of use cases. Every sentence adds value, and there is no redundancy.

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

  Completeness5/5

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

  Given the rich annotations and full schema coverage, the description adequately explains the return values (full content, media URLs, targeting info, run dates). No output schema exists, so the description fills that gap well.

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

  Parameters3/5

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

  Schema coverage is 100% with descriptions for all three parameters. The description adds minor value by noting creativeId comes from get_advertiser_ads results, but does not elaborate further. Baseline 3 is appropriate.

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

  Purpose5/5

  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 'ad creative' from Google Ads Transparency Center, with specific use cases listed. It distinguishes from siblings like get_advertiser_ads and get_advertiser_profile by focusing on a single ad's details.

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

  Usage Guidelines4/5

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

  The description provides explicit scenarios for using the tool (e.g., get full ad copy, targeting info, political ad ranges). It does not explicitly state when not to use it, but the context implies it's for deep dives after obtaining a creative ID from get_advertiser_ads.

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

• get_advertiser_profileA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. Description adds behavioral context by specifying the return fields (name, verification status, ad counts by format, platforms), which helps the agent understand what data to expect.

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

  Conciseness5/5

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

  Description is concise with four sentences and bullet points. It front-loads the core purpose and then lists specific uses, making it easy to parse quickly.

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

  Completeness5/5

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

  Given the simple two-parameter tool with no output schema, the description fully covers what the tool returns and its overall behavior. The annotations further reinforce safety, leaving no gaps for an AI to misunderstand.

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

  Parameters3/5

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

  Schema coverage is 100% with descriptions for both parameters (advertiserId and region). The description does not add extra meaning beyond the schema, as it does not elaborate on parameter usage or constraints.

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

  Purpose5/5

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

  Description clearly states verb 'Get' and resource 'summary profile of an advertiser's ad activity'. The bullet points detail specific outputs (verification status, ad counts, format distribution, platforms), effectively distinguishing it from siblings like get_advertiser_ads (which returns ad list) and search_advertiser.

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

  Usage Guidelines4/5

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

  Description explicitly lists four usage scenarios with bullet points (e.g., 'Get an overview of a brand's advertising presence'). However, it does not mention when NOT to use this tool or compare it to alternatives among siblings, missing a chance to guide selection.

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

• search_advertiserA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true. The description adds value by specifying the exact return fields (advertiser ID, name, verification status, total ad count), which is not present in annotations or schema. No contradictions.

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

  Conciseness5/5

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

  The description is succinct, with a clear opening sentence followed by three bullet points that are front-loaded and easy to scan. Every sentence adds value without redundancy.

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

  Completeness5/5

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

  For a search tool with no output schema, the description adequately covers return fields. Parameters are fully documented in schema, sibling tools provide context, and annotations declare safety traits. No apparent gaps.

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

  Parameters3/5

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

  Schema coverage is 100%, with clear descriptions for both 'query' and 'region' parameters. The description adds examples ('nike.com', 'Nike') but does not provide new semantic meaning beyond the schema. Baseline 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the tool searches for an advertiser by domain or brand name on Google Ads Transparency Center, and lists specific use cases (finding competitor ID, brand analysis, discovering related advertisers). It distinguishes from sibling tools like get_advertiser_profile and get_advertiser_ads by focusing on search/discovery rather than details or comparison.

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

  Usage Guidelines4/5

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

  The description provides explicit usage scenarios ('Use this tool to:') with three bullet points, guiding when to use it (e.g., find competitor ID, search brands). It does not explicitly mention when not to use or alternative tools, but the context of sibling tools implies differentiation.

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