Server Quality Checklist

Tool Scores

• list_accessible_customersA
  4/5.0
  Behavior3/5

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

  No annotations are provided. The description correctly indicates a read operation ('list'), but does not disclose potential behaviors such as pagination, rate limits, or error cases. For a parameterless tool, the transparency is acceptable but minimal.

  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 a single concise sentence with no unnecessary words. It is front-loaded with the action and resource.

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

  Completeness4/5

  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 no output schema, the description is nearly complete. It could mention the return type (a list), but the purpose is clear. The simplicity justifies a slight deduction.

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

  Parameters4/5

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

  The input schema has zero parameters with 100% coverage. The description adds no parameter details, which is appropriate since there are none. Baseline 4 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 explicitly states the action ('List'), the resource ('Google Ads customer ids'), and the context ('the authenticated user can access'). It clearly distinguishes from sibling tools 'search' and 'describe_resource'.

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

  Usage Guidelines3/5

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

  The description implies when to use this tool (to get a list of accessible customers), but provides no explicit guidance on when not to use it or alternatives. Given the simplicity and distinct sibling names, the implied usage is adequate.

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

• describe_resourceA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description must disclose behavioral traits. It states the tool 'discovers' fields, implying a read-only operation, and mentions it helps build GAQL. However, it does not elaborate on side effects, permissions, rate limits, or response format. The description is minimal but sufficient for a simple introspection tool.

  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 sentences plus an args section. It immediately states the purpose and then explains the parameter. Every sentence adds value, with no fluff. It is well-structured and front-loaded.

  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 is simple with one parameter and no output schema. The description covers the purpose and parameter details. It does not describe return values, but for a discovery tool, the context is largely complete. Sibling tools are distinct, so no extra differentiation needed. A slightly richer description of output would improve it.

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

  Parameters5/5

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

  The input schema has 0% description coverage, so the description must compensate. It does so effectively by explaining the parameter 'resource' as 'A resource/metric/segment prefix, e.g. 'campaign', 'ad_group', 'metrics', 'segments.' This adds concrete examples and context beyond the schema's type and title, making the parameter's meaning clear.

  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's purpose: 'Discover selectable/filterable fields of a resource to help build GAQL.' It uses a specific verb ('Discover') and resource ('fields of a resource'). The tool name 'describe_resource' matches the purpose, and sibling tools (list_accessible_customers, search) are distinct, making the tool's role clear.

  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 explains when to use the tool: 'to help build GAQL' and provides example resource prefixes. It does not explicitly exclude other tools or state when not to use it, but given the distinct siblings (search for executing queries, list_accessible_customers for listing customers), the usage context is fairly clear.

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

• searchA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden. It discloses key behaviors: customer_id dashes are stripped, default page_size, and login_customer_id for manager accounts. However, it does not discuss auth, rate limits, or error responses.

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

  Conciseness4/5

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

  The description is front-loaded with the main action and then lists arguments clearly. It is concise without extraneous information, though it could be slightly shorter by omitting redundant phrasing like 'Args:'.

  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?

  Given 4 parameters, no output schema, and no annotations, the description covers the parameters well and explains their usage. It lacks details on return format, pagination beyond page_size, and error handling, but is sufficient for a search tool.

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

  Parameters5/5

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

  The input schema has 0% description coverage (only titles), so the description adds essential meaning: customer_id is an account id with dashes stripped, gaql is a GAQL statement, page_size defaults to 1000, and login_customer_id is optional for manager accounts. This is critical for correct usage.

  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 it runs a GAQL query against one account and returns matching rows. The verb 'run' and resource 'GAQL query' are specific, and it distinguishes from siblings like list_accessible_customers and describe_resource.

  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 explains when to use it (run GAQL queries) and provides context for parameters, but does not explicitly state when not to use it or mention alternatives. However, the purpose is clear enough for an agent to decide.

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