Server Quality Checklist

Tool Scores

• update_ad_groupA
  3.8/5.0
  Behavior3/5

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

  Annotations already indicate mutation (readOnlyHint=false) and idempotency (idempotentHint=true). Description adds context about money fields being in account currency and points to sibling for status changes. However, it lacks details on permissions, side effects, or response format. With annotations present, it provides moderate added value.

  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?

  Two efficient sentences. First sentence delivers purpose and scope (list of updatable fields, currency note). Second sentence provides key usage guidance. No filler. Front-loaded with primary action.

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

  Completeness3/5

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

  No output schema exists, so description should cover return behavior or errors. It does not. It also doesn't explain partial update behavior (only provided fields are updated) or validation of nested objects (extra, targetings). For an 8-parameter tool with nested structures, more context would be beneficial. However, schema covers all parameters, so baseline is adequate.

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

  Parameters2/5

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

  Schema coverage is 100%, so all parameters are documented in the schema. The description merely lists field categories ('name, budgets, bid cap, dates or targeting'), which is redundant. It adds no extra meaning beyond what schema already provides. Not harmful but unnecessary.

  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 updates an ad group's specific fields (name, budgets, bid cap, dates, targeting). It also distinguishes itself from the sibling tool 'ad_group_action' for status changes. The verb 'Updates' + resource 'ad group' is precise.

  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 directs to use 'ad_group_action' for status changes, providing a clear alternative. It implies this tool is for non-status updates but does not explicitly state when not to use it. Needs more exclusion criteria but sufficient for differentiation.

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

• list_ad_groupsA
  3.9/5.0
  Behavior4/5

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

  Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds valuable behavioral context beyond annotations: it notes that money fields are in account currency and that targetings contains specific targeting structure, which helps the agent understand output format.

  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 extremely concise (two sentences) with no wasted words. The main action is front-loaded, and every sentence adds unique value.

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

  Completeness3/5

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

  No output schema is provided. The description mentions money fields and targetings but omits pagination behavior (offset, limit, autoPaginate) and the overall return structure (e.g., list of objects). Given the tool's complexity (7 params, no output schema), the description is somewhat under-specified.

  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?

  All 7 parameters are fully described in the schema (100% coverage). The description adds overarching context about money fields and targetings, which complements the schema without repeating it. This extra nuance elevates the score above baseline 3.

  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 lists ad groups with optional filtering by ids, parent ad plans, and statuses. It also specifies that money fields are in account currency and that targetings holds targeting structure, which distinguishes it from sibling list tools like list_ad_plans or list_banners.

  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 does not provide explicit guidance on when to use this tool versus alternatives (e.g., list_ad_plans, list_banners). It implies usage for ad group listing but lacks exclusion criteria or context for tool selection.

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

• update_bannerA
  3.9/5.0
  Behavior3/5

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

  Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds that structures are sent verbatim, which is useful. No contradictions. But it does not disclose other behaviors like rate limits or auth needs. With annotations carrying part of the burden, the description adds moderate value.

  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?

  Two concise sentences. The first clearly states the action and affected fields. The second adds essential usage guidance about verbatim structures and the alternative tool for status changes. No wasted words.

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

  Completeness3/5

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

  With no output schema, the description does not explain return values. While the purpose and parameters are clear, the tool could benefit from stating whether it returns the updated banner or a success message. For a 5-parameter tool with good annotations, it is adequate but not complete.

  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 baseline is 3. The description reinforces that structures are sent verbatim, aligning with schema descriptions. It does not add new meaning beyond what the schema provides, so score remains at baseline.

  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 uses specific verb 'Updates' and resource 'banner', listing fields (name, text blocks, links). It distinguishes from sibling 'banner_action' which changes status, and from 'create_banner'. This clearly identifies the tool's purpose among siblings.

  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?

  Explicitly directs users to 'banner_action' for status changes, providing an alternative. It gives context on how to use the tool by stating that structures are sent verbatim. However, it does not specify prerequisites or when not to use this tool, missing some guidance.

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

• ad_plan_actionA
  4/5.0
  Behavior4/5

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

  Annotations already indicate destructiveHint=true, and the description confirms the behavioral impact by mapping each action to a specific status change. It adds context beyond annotations by detailing the status transitions, though it omits potential side effects like cascading deletions.

  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, well-structured sentence that immediately conveys the purpose and available actions. No unnecessary words or repetition.

  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?

  For a simple mutation tool with two parameters and no output schema, the description covers the essential behavior and parameter mappings. It lacks information about return values or errors, but for a status-change tool, this is sufficient.

  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 description explains the 'action' parameter by linking each enum value to its resulting status (e.g., activate -> status=active), which adds meaning beyond the schema's enum definition. For 'ids', the schema already provides a clear description. With 50% schema coverage, the description partially compensates.

  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 action (changes lifecycle status), the resource (ad plans by id), and the specific available actions (activate, stop, delete) with their resulting statuses. This distinguishes it from sibling tools like ad_group_action and banner_action.

  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 does not provide any guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. It simply states what it does without context.

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

• banner_actionA
  4/5.0
  Behavior3/5

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

  Annotations already declare destructiveHint=true and readOnlyHint=false, so the description minimal additional transparency. It does add the specific status values, but does not detail side effects, authorization, or reversibility.

  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?

  Single sentence, no filler, front-loaded with verb and resource. Every word earns its place.

  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?

  Adequate for a simple mutation tool with two parameters and annotations present. Could optionally mention batch operation semantics (e.g., whether multiple ids are processed atomically), but overall sufficient.

  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?

  Schema description coverage is 50% (only ids has description). The description enhances understanding by mapping the action enum to status values, which the schema lacks. This adds value beyond the schema.

  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 changes lifecycle status of banners by ID, listing the three specific actions (activate, stop, delete) with their status values. It distinguishes from sibling tools like ad_group_action and update_banner by focusing solely on status mutations.

  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?

  No explicit guidance on when to use this tool versus alternatives like update_banner or delete_banner. The description implies use for lifecycle changes, but does not specify exclusions or context.

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

• get_throttlingA
  4/5.0
  Behavior3/5

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

  Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. Description adds that it returns current limits and remaining budget. No contradiction, but no additional behavioral details beyond 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?

  Single, efficient sentence with no wasted words. Front-loaded purpose.

  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?

  No output schema, but description covers purpose and return content. For a simple read-only tool, it is mostly complete.

  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?

  No parameters in schema (100% coverage). Description adds no parameter info, but baseline for zero params is 4.

  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 it returns VK Ads request limits and remaining budget, with a clear purpose to avoid rate limits. Distinct from sibling tools like get_balance or get_statistics.

  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?

  Description implies when to use (before making requests to check limits), but no explicit when-not or alternatives. Given simplicity, it's adequate but not explicit.

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

• get_user_infoA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true, so the agent knows this is a safe, idempotent read operation. The description adds the detail that it returns account info including client_name, but does not disclose additional behavioral traits like authorization needs or rate limits. With comprehensive annotations, a score of 3 is appropriate.

  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 two sentences long, front-loads the main purpose, and includes a use case. Every sentence adds value without redundancy or fluff.

  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's simplicity (one optional parameter, no output schema, rich annotations), the description is fairly complete. It states what is returned and why to use it. Minor improvements could include mentioning the absence of output schema or pagination, but it is sufficient for an agent to use effectively.

  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 input schema has one optional parameter (fields) with 100% schema description coverage. The description does not add extra meaning beyond the schema; it only mentions that the tool returns account info, not how the 'fields' parameter affects the output. Baseline 3 is correct since schema covers the parameter.

  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 that the tool returns information about the current VK Ads account, including specific fields like additional_info.client_name. This provides a specific verb and resource, distinguishing it from sibling tools such as get_balance or get_statistics.

  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 when to use the tool: to confirm which advertiser account the token points at. While it does not mention when not to use it or alternative tools, the guidance is clear and actionable.

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

• list_ad_plansA
  4/5.0
  Behavior4/5

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

  The description adds value beyond annotations by noting that money fields are in account currency. Annotations already indicate readOnly, idempotent, and non-destructive behavior, so the description's addition of currency context is helpful.

  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?

  Two concise sentences, front-loaded with purpose and key detail about currency. No extraneous information.

  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 6 parameters and no output schema, the description covers the core purpose and adds a helpful detail about currency. It lacks explanation of pagination behavior, but the schema describes pagination parameters sufficiently. Overall, it is fairly complete for a 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%, so the baseline is 3. The description mentions filtering by id and status, which maps to the ids and statuses parameters, but this is already clear from the schema. It does not significantly enhance parameter understanding beyond the schema.

  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 lists ad plans (campaigns), specifies it's the top-level object, and mentions optional filtering by id and status. This distinguishes it from sibling tools like create_ad_plan and update_ad_plan.

  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 does not explicitly state when to use this tool versus alternatives (e.g., create_ad_plan for creation). However, the name and context of sibling tools imply it's for reading, and the annotation readOnlyHint reinforces this. No explicit guidance on exclusions.

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

• list_bannersA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds that moderation_status and delivery show why an ad is or isn't showing, which provides some behavioral context beyond the annotations. However, it does not elaborate on pagination behavior or other details.

  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?

  Two sentences, each serving a purpose. The first states the main action, the second adds relevant detail. No superfluous words.

  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?

  For a simple list tool with no required parameters and robust annotations, the description adequately covers the key filtering options and the purpose of moderation fields. It is complete enough for its complexity, though it could mention the response format.

  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?

  All 7 parameters have full schema descriptions (100% coverage). The description mentions filtering by id, ad group, and status, but does not add significant 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 'Lists banners' specifying the verb and resource. It further distinguishes the tool from sibling tools like banner_action or create_banner by indicating it's a listing operation with optional filtering.

  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 lists filtering options (by id, parent ad group, status) and mentions moderation_status and delivery for understanding ad visibility. This provides clear usage context, though it does not explicitly state when not to use the tool or mention alternatives.

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

• create_ad_planA
  4.1/5.0
  Behavior4/5

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

  Annotations already indicate it is a mutation (readOnlyHint=false) and not destructive. The description adds useful behavioral context: money fields use account currency, and the 'extra' field merges verbatim into the request body. This goes beyond the annotations, though it doesn't describe return behavior or 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.

  Conciseness5/5

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

  Three short sentences, no fluff. The most important info (creates an ad plan) is first. Every sentence adds value: creation action, currency context, and extra field usage.

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

  Completeness3/5

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

  Given the tool's complexity (9 parameters, nested objects, no output schema), the description is adequate but lacks information about what the tool returns (e.g., the created ad plan ID or full object). With openWorldHint=true, some gaps are acceptable, but for a creation tool, return behavior is expected.

  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?

  Schema coverage is 100% with descriptions for all parameters. The description adds meaning by clarifying that money fields are in account currency and that 'extra' is for complex fields. This raises it above the baseline of 3, as it provides practical currency context and usage hints.

  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 'Creates an ad plan (campaign)', which is a specific verb+resource. The title 'Create ad plan (campaign)' aligns perfectly, and the sibling list includes 'update_ad_plan' and 'ad_plan_action', making the purpose distinct.

  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 mentions that money fields are in account currency and that complex fields should be passed via 'extra'. However, it lacks explicit guidance on when to use this tool versus alternatives like 'update_ad_plan' or 'ad_plan_action', and does not mention any prerequisites or context.

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

• get_regionsA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds that results include id, name, and type, and that filtering is case-insensitive. This adds moderate value beyond the annotations but does not disclose additional traits like pagination or rate limits.

  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 extremely concise—two sentences with no wasted words. It is front-loaded with the main action and filter option, followed by practical context. Every sentence earns its place.

  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 tool's simplicity (2 optional params, no output schema), the description is complete: it explains what the tool returns, its filter, and its use case. No output schema is present, so the description adequately covers the return structure by listing fields.

  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 both parameters (limit, query) well-documented in the input schema. The description reinforces the filtering capability but does not add new semantics beyond what the schema already provides.

  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 that the tool lists VK Ads geo regions with specified fields (id, name, type) and supports optional filtering by name substring. It also explains the practical need for region IDs in ad group targeting, making the purpose distinct from sibling tools like get_statistics or list_ad_groups.

  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 a clear use case (obtaining region IDs for ad group geo targeting) but does not explicitly state when not to use it or mention alternatives. The context is sufficient for an agent to understand the intended usage.

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

• create_bannerA
  4.2/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=false and openWorldHint=true. The description adds context that structures are passed verbatim and external documentation is needed for exact shape, which is consistent and informative 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?

  Two sentences: the first states the core purpose, the second clarifies parameter usage and directs users to external docs. No redundant information; every sentence earns its place.

  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?

  For a creation tool with 6 parameters and no output schema, the description covers parameter roles and points to external docs for complex shapes. It does not mention the return value (e.g., banner ID) but given context, it is mostly adequate.

  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?

  Schema coverage is 100% with descriptions, but the description adds value by grouping parameters (content, textblocks, urls) and explaining their roles (media references, ad copy, links). This holistic view improves understanding beyond individual schema descriptions.

  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 creates a banner within an ad group, distinguishing it from sibling tools like update_banner (update vs. create) and create_ad_group (different resource). The verb 'creates' and resource 'banner' are specific.

  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 the tool is for creating banners inside ad groups but does not explicitly state when to use it over alternatives like raw_request or other creation tools. No when-not or exclusion criteria are given.

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

• get_balanceA
  4.2/5.0
  Behavior4/5

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

  Annotations declare readOnly and idempotent. Description adds that it returns the raw VK response unchanged and notes uncertainty about field names, which is valuable behavioral context beyond annotations.

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

  Conciseness3/5

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

  Description is verbose, including detailed explanation of field uncertainty and defensive parsing. While informative, it could be trimmed for conciseness.

  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?

  Covers key aspects: return content (balance, currency), raw format, defensive note. Lack of output schema is partly compensated by describing field paths. Still, could be more explicit about exact structure.

  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?

  No parameters (schema coverage 100%), so baseline 4. Description confirms no parameters and explains that the token determines the account, adding use context.

  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 the VK Ads account balance (available funds and currency), referencing specific fields. It distinguishes from siblings by being the only balance-retrieval tool.

  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?

  Implicitly indicates usage (no parameters, uses token's account) but lacks explicit when-to-use or when-not-to-use guidance. Since it's the sole balance tool, context is clear.

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

• get_statisticsA
  4.3/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral context beyond annotations: default grouping, meaning of total field, metrics location under base. No contradiction with annotations.

  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 dense paragraph without wasted words. It could benefit from slight restructuring (e.g., bullet points for parameter guidance), but the content is efficient and front-loaded with core purpose.

  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 11 parameters, no output schema, and rich annotations, the description covers key behavioral aspects (grouping, total, metrics). It lacks details on pagination beyond autoPaginate hint, but overall provides sufficient context for an agent to use correctly.

  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?

  Schema description coverage is 100%, so baseline is 3. The description adds value by explaining the default period, the total field, and examples for sortBy (e.g. base.spent). This improves clarity beyond the raw schema.

  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 'Fetches performance statistics from the VK Ads v3 statistics service for ad plans, ad groups or banners.' It uses a specific verb ('fetches'), identifies the resource ('performance statistics'), and distinguishes from sibling tools that are CRUD or info retrieval tools.

  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 usage guidance on period grouping ('by default the grouping is `summary` — one aggregated row per object over the whole period; use day/week/month ONLY for daily dynamics or trend questions') and explains sorting and total field. Though it doesn't explicitly state when not to use this tool vs alternatives, the context of siblings (mostly CRUD) makes this clear enough.

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

• ad_group_actionA
  4.4/5.0
  Behavior4/5

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

  The description adds context beyond annotations by mapping each action to a specific status (active, blocked, deleted). Annotations already mark it as destructive (destructiveHint=true) and not idempotent, which aligns with the delete action. 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?

  A single sentence that efficiently conveys the tool's purpose and parameter meaning without any superfluous words. Front-loaded with the main action.

  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's simplicity (2 required parameters, no output schema), the description is complete enough for correct invocation. It could optionally mention that the operation is irreversible for delete, but that is implied by the destructive annotation.

  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 schema has 50% description coverage (ids parameter described, action parameter not). The description compensates by explaining the meaning of each action value, which adds value beyond the schema's enum definition.

  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 changes the lifecycle status of ad groups by id, specifying three actions (activate, stop, delete) and their corresponding status values. This distinguishes it from sibling tools like ad_plan_action (different resource) and update_ad_group (likely for other modifications).

  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 implies usage for lifecycle management of ad groups, but does not explicitly state when to use this tool versus alternatives like update_ad_group or create_ad_group. However, the context is clear enough for an AI agent to infer its specific purpose.

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

• create_ad_groupA
  4.4/5.0
  Behavior4/5

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

  Annotations indicate mutation (readOnlyHint=false) and openWorldHint=true. Description adds context on targeting format, currency, and extra field merging, which is beyond annotation details.

  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?

  Three sentences front-load the purpose, then provide critical usage details. No wasted words.

  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?

  Covers main usage points despite no output schema and complex parameters. Could mention return value, but not required and still complete for invocation.

  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?

  With 100% schema coverage, baseline is 3. Description adds value by explaining targeting structure with an example, money field currency, and the extra field's role, improving over schema descriptions.

  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 states 'Creates an ad group inside an ad plan' with a clear verb and resource. It distinguishes from siblings like update_ad_group and list_ad_groups.

  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?

  Provides specific guidance on targeting structure, money field currency, and the extra field. Lacks explicit when-not-to-use or alternatives, but creation context is clear.

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

• raw_requestA
  4.4/5.0
  Behavior4/5

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

  Annotations readOnlyHint=false and destructiveHint=true are consistent. Description adds context: escape hatch nature, confirmWrite requirement for writes, and that GET runs freely. No mention of rate limits or auth specifics, but provides sufficient behavioral context beyond 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?

  Three sentences with clear front-loading of purpose. Each sentence adds necessary information; no fluff or redundancy.

  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?

  Covers input parameters and behavioral rules well. No output schema, but for an escape hatch returning arbitrary data, describing return format is less critical. Missing error handling details, but overall adequate given tool complexity.

  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?

  Schema coverage is 100%, baseline 3. Description adds meaning: explains query becomes query string, body as JSON for POST, confirmWrite must be true for writes. This adds value over the parameter descriptions in the schema.

  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?

  Clearly states it is an escape hatch to call any VK Ads API endpoint directly, with an example path and method. Distinguishes from dedicated sibling tools by being the generic fallback.

  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?

  Explicitly says 'Use this for endpoints that have no dedicated tool' and explains when GET is free versus POST/DELETE requiring confirmWrite. Does not explicitly say to prefer dedicated tools when available, but implied.

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

• update_ad_planA
  4.4/5.0
  Behavior4/5

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

  Annotations already indicate mutation (readOnlyHint=false), idempotency, and non-destructive nature. Description adds context that money fields are in account currency. No contradictions and adds some behavioral detail.

  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?

  Two short sentences, front-loaded with key information. Every word earns its place. Efficient and clear.

  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?

  No output schema, but update tool typically returns updated object or success; description omits this. However, annotations and sibling context provide enough to infer. Could mention idempotency or extra field behavior, but overall adequate for a straightforward update.

  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%, so description adds minimal extra value. It repeats 'account currency' for money fields and explains 'extra' parameter similarly to schema. Adequate but not enhancing beyond baseline.

  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?

  Clear verb 'Updates' and specific resource 'ad plan' with explicit fields (name, budgets, bid cap, dates). Distinguishes from sibling tool ad_plan_action for status changes.

  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?

  Explicitly says 'Use ad_plan_action to change status', providing clear when-not guidance. Implies use for updating fields, no confusion with alternatives.

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