Server Quality Checklist

Tool Scores

• search_searchC
  2.9/5.0
  Behavior2/5

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

  The readOnlyHint annotation already indicates this is a read operation, and the description adds no behavioral detail beyond that: no mention of pagination, rate limits, result shape, or side effects. 'Fetches data' essentially restates the annotation rather than enriching it.

  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 a single concise sentence with no filler and the key verb is front-loaded. It could have packed in more useful detail without becoming bloated, but as written it is appropriately sized for a minimal definition.

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

  Completeness2/5

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

  Despite a rich schema and an output schema, the description leaves out critical context: why to use this instead of the siblings, what 'search method' means in practice, and any constraints or caveats about the query. For a generic data-fetching tool with six parameters, this is under-specified.

  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 the parameters are already well documented. The description does not add any extra meaning about how parameters like fields, resource, or conditions should be used, so the baseline of 3 applies.

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

  Purpose4/5

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

  The description uses a specific verb ('Fetches') and identifies the resource ('data from the Google Ads API') with a named method ('search method'). It is clear enough to understand the basic operation, but it does not distinguish this tool from the sibling tools customers_list_accessible_customers or metadata_get_resource_metadata, so it earns 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.

  Usage Guidelines2/5

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

  The description gives no guidance about when to use this tool versus the listed sibling tools, and it does not mention any exclusions or alternative approaches. An agent cannot tell from the description whether to choose this tool or one of its siblings in a given situation.

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

• metadata_get_resource_metadataA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, so the description correctly aligns with that. It adds behavioral context beyond the annotation: field name prefixes ('metrics.' and 'segments.'), the relationship to query construction, and that responses should be cached because they don't change frequently. No contradiction or hidden side effects.

  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 well-structured and front-loaded with the core function, followed by usage guidance, a mandatory instruction, and caching advice. There is minor redundancy between the first sentence's 'including compatible metrics and segments' and the later sentence repeating that metrics/segments are returned, but overall every sentence contributes.

  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?

  The tool is simple (one fully documented parameter, read-only annotation, output schema present), and the description covers what the tool returns, how to use it, why it must be used before `search`, and caching behavior. Nothing an agent needs to call it correctly is missing.

  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?

  The schema already covers the only parameter fully with a description and example. The description reinforces the example ('campaign', 'ad_group') but does not add much beyond what the schema provides. With 100% schema_description_coverage, 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 uses a specific verb ('Retrieves') with a clear resource ('selectable, filterable, and sortable fields for a specific Google Ads resource') and explicitly mentions metrics and segments. It distinguishes itself from the sibling `search` tool by framing itself as the discovery step before querying.

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

  Usage Guidelines5/5

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

  The description gives explicit when-to-use guidance: 'Use this tool to find out which fields you can select, filter by, or sort by when querying a specific resource.' It also states a hard rule: 'Do not guess fields, you MUST use this tool to discover them before constructing a query for the `search` tool.' This clearly routes an agent to the correct workflow.

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

• customers_list_accessible_customersA
  4.5/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true, which aligns with the description's read-only nature. The description adds value beyond annotations by noting that it returns only directly accessible customershare, implying a permission filter, and that the output is a list of IDs (though this is also in the output schema). It does not contradict 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 brief purpose statement and a usage hint, followed by a return type section. It is front-loaded with the key action and avoids unnecessary detail.

  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 parameterless tool with a simple output (a list of strings), the description is fully sufficient. It explains what the tool does, when to use it, and what it returns. The output schema already documents the return type, so no additional return detail is needed.

  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 tool has zero parameters, so there is no parameter semantics to clarify. The description correctly focuses on the output and usage context, which is appropriate for a parameterless tool.

  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 returns IDs of customers directly accessible by the authenticated user, with a specific verb ('Returns') and resource ('customers'). It is distinct from siblings like search_search and metadata_get_resource_metadata, as it lists customer IDs rather than performing search or fetching metadata.

  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 explicitly tells the agent to use this tool first to discover customer IDs if the user hasn't provided one, and notes that most other tools require a valid customer ID. It does not explicitly mention when not to use it or name alternatives, but the guidance is clear enough for this context.

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