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

No annotations are provided, so the description must fully disclose behavior. It mentions the dry_run parameter for validation but does not discuss side effects, authorization requirements, rate limits, or what happens on success/failure beyond the return value.

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 uses a clear Args/Returns structure but includes parameter descriptions that could be redundant given the schema. It could be slightly more concise without losing clarity.

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 tool with 5 parameters and an output schema, the description covers all parameters and hints at the return value. However, the output schema is not detailed in the description, but the return mentions success status and count. Overall sufficient for the tool's complexity.

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 compensates by explaining each parameter's purpose, including match_type values and dry_run behavior. However, it could be more detailed about the format of keywords (e.g., case sensitivity) and customer_id 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 clearly states the tool's purpose: 'Add keywords to an ad group.' The parameters further clarify the action, and the sibling tools include 'add_negative_keywords', which distinguishes this tool as adding positive keywords.

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 context (adding keywords to an ad group) but does not explicitly state when to use this tool versus alternatives like 'add_negative_keywords' or other ad group operations. No guidance on prerequisites or exclusions.

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 discloses key behavioral traits: level specificity (campaign vs ad group), mutual exclusivity of IDs, and the dry_run validation feature. It also mentions return values. Missing details like destructive potential or permissions, but adequate for a low-risk mutation 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 description is concisely front-loaded with purpose, followed by structured Args, Note, and Returns sections. Every sentence adds value without redundancy. Efficiently communicates all necessary information.

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 complexity (6 parameters, mutual exclusivity constraint) and the presence of an output schema, the description is complete. It explains parameters, constraints, behavior, and expected return, leaving no significant gaps for the agent to operate correctly.

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 parameters. It does so comprehensively: keywords (list), customer_id (optional), campaign_id and ad_group_id with mutual exclusivity note, match_type with options, and dry_run behavior. Adds significant meaning beyond the schema's titles and defaults.

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 'Add negative keywords to block irrelevant searches,' providing a specific verb and resource. It distinguishes itself from sibling tool 'add_keywords' by specifying 'negative' keywords, making the purpose unambiguous.

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 explains when to use the tool (to block irrelevant searches) and provides clear context on choosing between campaign-level and ad group-level exclusions. However, it does not explicitly mention when not to use it or compare with alternatives like 'add_keywords', but the context is sufficient for correct usage.

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 bears full responsibility for behavior. It explains parameters, defaults, and the dry_run option for validation. However, it does not mention side effects, permissions, or error handling, which would improve transparency.

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 and well-structured, with a one-line summary, a bulleted Args list, and a Returns section. Every sentence provides necessary information without 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 5 parameters and states the return value. It could mention prerequisites like campaign existence, but for a create operation with 2 required fields, it is sufficiently complete.

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 input schema has 0% description coverage, so the description compensates fully. It explains each parameter, including units for cpc_bid_micros (e.g., '1,000,000 = $1.00') and default values, adding significant meaning beyond the schema's bare types and titles.

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 'Create an ad group in a campaign', specifying the action (create) and the resource (ad group). This distinguishes it from sibling tools like create_campaign or create_responsive_search_ad, which target different entities.

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 explains what the tool does but does not provide explicit guidance on when to use it versus alternatives or when not to use it. The context of ad group creation is implied but not elaborated.

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?

Without annotations, the description fully discloses default paused status, dry_run behavior, default budget, and return structure. No contradictory or hidden destructive traits are mentioned.

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?

Well-organized with a succinct intro, bulleted args, and return section. Efficient but could be slightly more compact without losing clarity.

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?

Fully covers 5 parameters, safety behavior, dry_run, and return values given no annotations and no enum constraints. Output schema handles return details, but description adds sufficient context.

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?

With 0% schema coverage, description compensates by explaining each parameter in detail, including examples for budget_amount_micros and advertising_channel_type, and defaults beyond the 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 'Create a new Google Ads campaign' and elaborates on creating campaigns with specific settings. It distinguishes from sibling tools like enable_campaign by noting campaigns start in PAUSED status.

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?

Explicitly advises using enable_campaign after creation, providing a clear workflow. Mentions dry_run for validation but lacks explicit when-not-to-use guidance for other scenarios.

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?

Explains RSA dynamic combination behavior and dry_run validation. No annotations exist, so description covers key behavioral traits like non-execution on dry run. Lacks notes on idempotency or error conditions, but adequate.

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?

Well-structured with Args/Returns sections, front-loaded purpose. Slightly long but every sentence adds value. Could be more terse without losing clarity.

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?

Covers all parameters, return value, and dry_run behavior. Lacks mention of prerequisites (e.g., ad group existence) or error handling, but given output schema and no annotations, it is largely complete.

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 description provides all parameter semantics: ad_group_id, headlines with count/char limit, descriptions with count/char limit, final_url, optional customer_id, path1/path2 max chars, and dry_run meaning. Adds significant value beyond 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?

Clearly states 'Create a responsive search ad (RSA)' and explains what RSA is. Verb+resource is specific and distinct from siblings, which lack other ad creation 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?

Provides required counts and character limits for headlines and descriptions, plus Google's recommendation for variations. Implicitly guides usage but does not explicitly state when to use vs other ad types (not needed given siblings).

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 briefly mentions the function and the dry_run parameter behavior, but does not disclose side effects (e.g., impact on other entities), permissions needed, or behavior when already enabled.

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 and well-structured with a clear header and docstring-style parameter list. No unnecessary information, though it could be slightly more compact.

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 an output schema exists, the description includes a return note, but lacks context on permissions, idempotency, or behavior in edge cases. Adequate but not comprehensive.

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?

Although schema has 0% coverage, the description explains each parameter's purpose concisely (e.g., ad_group_id as ID to enable, customer_id as optional, dry_run for validation). This adds value beyond the type-only 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 the action (enable) and resource (ad group). It distinguishes from siblings like pause_ad_group by the action verb, but does not explicitly differentiate from create_ad_group or others.

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?

No guidance on when to use this tool versus alternatives like pause_ad_group or create_ad_group. No mention of prerequisites or context.

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 must cover behavioral traits. It mentions that enabling starts ad serving and explains the dry_run parameter's validation behavior. However, it does not disclose whether the tool is idempotent (e.g., enabling already enabled campaign) or any authorization requirements, leaving some gaps.

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 clear purpose statement, a brief usage note, and structured Args/Returns sections. Every sentence adds value with 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?

The description covers the tool's purpose, prerequisites, and parameter behaviors. Since an output schema exists, it's acceptable not to detail the return structure. However, it lacks mention of edge cases like enabling an already enabled campaign, which would be beneficial.

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?

With 0% schema description coverage, the description adds crucial meaning: explains campaign_id as the ID to enable, customer_id as optional if set in config, and dry_run as a validation-only mode. This goes beyond the bare schema types and defaults.

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 explicitly states 'Enable a campaign' and clarifies that enabling starts ad serving. This clearly identifies the tool's action and resource, distinguishing it from siblings like pause_campaign or create_campaign.

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 provides essential context by advising that budget, targeting, and ads should be configured before enabling. It does not explicitly mention when not to use the tool or list alternatives, but the context is sufficient for correct usage.

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, description carries burden. It correctly labels as read operation, but does not cover potential errors, rate limits, or pagination behavior. Returns format is briefly explained.

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?

Description is concise with useful examples. Could omit some redundancy, but overall well-structured and front-loaded with purpose.

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 no annotations and presence of output schema, description adequately covers basic usage. Lacks detail on error handling and result limits, but sufficient for typical agent 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 coverage is 0%, so description compensates by explaining query as GAQL string with examples, and customer_id as optional digits-only. Provides meaningful context beyond 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 the tool executes GAQL queries for read operations, provides common query examples, and distinguishes from sibling tools which are all write-oriented.

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?

Explicitly says 'use for any read operation' and implies not for mutations via sibling tool list. Provides examples and optional parameter explanation, but lacks explicit when-not-to-use guidance.

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 provided, but description fully explains behavior: lists accounts, returns specific fields, no side effects. Sufficient for a read-only list operation.

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?

Three sentences, front-loaded purpose, no extraneous words. Efficient and clear.

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?

Zero parameters, simple list operation. Description covers purpose, output fields, and return type. Output schema exists, so return value details are not required.

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?

No parameters exist, so baseline 4 applies. Description does not need to add parameter info.

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?

Clearly states it lists Google Ads accounts accessible by the credential, and specifies output fields (customer_id, resource_name). Distinguishes from siblings which are mutating or query tools for campaigns/ads.

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?

No explicit guidance on when to use vs alternatives. Implicitly suggests usage before other operations to obtain customer IDs, but lacks when-not-to-use or alternative references.

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 must disclose behavioral traits. It mentions 'dry_run' for validation without execution and returns a success status. However, it does not describe side effects, required permissions, or what happens to the ad group if paused (e.g., active campaigns, lapsing).

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?

Extremely concise and well-structured. The purpose is stated in one line, followed by clear parameter descriptions in Args format, and a Returns line. No unnecessary words.

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 simple mutation tool with 3 parameters and an output schema, the description covers purpose, parameters, and return value. However, it lacks usage guidelines and behavioral context. With no annotations, it is minimally viable but not fully complete.

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 compensate. It explains each parameter: ad_group_id (required), customer_id (optional with config hint), and dry_run (validation mode). This adds meaningful context beyond the schema definition.

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 verb and resource ('Pause an ad group'). It distinguishes from sibling tools like 'enable_ad_group' and 'create_ad_group'. However, it does not differentiate from 'pause_campaign' or clarify any special scope.

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?

No guidance on when to use this tool versus alternatives like 'enable_ad_group' or 'pause_campaign'. No prerequisites or context for when pausing is appropriate.

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?

Since no annotations are provided, the description carries the full burden. It discloses that pausing stops ad serving but preserves settings and history, and explains the dry_run parameter's validation-only behavior. However, it does not mention reversibility or error states.

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 sentence explaining the action, followed by a structured Args list. No unnecessary words, and the key information is front-loaded.

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 simplicity of the tool (3 parameters, no nested objects), the description covers the main effect, parameter meanings, and return value. It could mention idempotency or behavior when already paused, but overall it is sufficiently complete.

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 input schema has 0% description coverage, so the description must compensate. The Args section adds clear semantics for all three parameters: campaign_id (what to pause), customer_id (optional, from config), and dry_run (validate vs execute). This fully compensates for the missing schema descriptions.

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 'Pause a campaign' and explains that it stops ad serving while preserving settings and history. It distinguishes from sibling tools like 'pause_ad_group' and 'enable_campaign' by specifying the resource (campaign) and action (pause).

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: use this tool to pause a campaign. However, it does not explicitly state when to use it versus alternatives like 'enable_campaign' or 'pause_ad_group', nor does it provide exclusions or prerequisites.

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 for behavioral context. It reveals that `dry_run` validates without executing, which is a key behavioral trait. However, it does not mention that updates are destructive, require permissions, or have rate limits. The return type is only vaguely described as 'Result with success status'.

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 efficient with a docstring format that front-loads the purpose. Every sentence adds value, though the 'Args' and 'Returns' sections could be slightly more compact. No extraneous information.

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 existence of an output schema (which complements the return description) and the thorough parameter explanations, the tool is adequately documented for a simple update operation. It covers the essential context without missing critical information.

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 explain each parameter. It does so thoroughly: `ad_group_id` is the target ID, `cpc_bid_micros` includes units (micros with an example), `customer_id` notes optionality, and `dry_run` explains its validation behavior.

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 'Update the CPC bid for an ad group.' with a specific verb and resource. This distinguishes it from sibling tools that deal with keywords, campaigns, or other entities, as no other tool updates ad group bids.

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 purpose is clear and implies when to use this tool (when updating a bid). However, it does not explicitly exclude alternative approaches or provide guidance on when not to use it. The sibling list lacks any bid-related alternatives, so no confusion exists.

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