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

With no annotations, the description carries full burden. It does not disclose whether keywords are appended or replaced, maximum keyword count, or whether customer_id affects scoping. Essential behavioral traits are missing.

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?

One sentence plus a list of match types; no verbose information. Could be slightly more structured (e.g., bullet points) but is appropriately concise.

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?

Despite an output schema handling return values, the description omits prerequisites (e.g., campaign must exist), side effects (e.g., duplicate handling), and error scenarios. For a 4-parameter mutation tool, this is incomplete.

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%, but description only clarifies match_type values. It does not specify keyword format (e.g., array of single words, comma-separated) or explain the optional customer_id parameter.

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: 'Attach campaign-level negative keywords' and lists allowed match types. It is distinguishable from sibling tools (e.g., pause_campaign, update_budget) which target different resources.

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 (e.g., ad group negative keywords). No when-not-to-use or prerequisites provided.

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 provided, the description carries full burden. It clearly states the action and effect (changing campaign status from PAUSED to ENABLED). However, it does not disclose potential error states (e.g., if campaign is already enabled) or permissions/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.

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

The description is a single, clear sentence with no unnecessary words. It is perfectly front-loaded and efficient.

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 tool has a simple input schema (2 params, 1 required) and an output schema is present. The description is minimal but sufficient for an agent to understand the core action. However, it lacks parameter descriptions and usage context beyond the basic purpose.

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% with no descriptions for the two parameters. The description does not add any meaning to the parameters beyond what the schema provides (types and required/optional). It should have compensated for the lack of 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 states the verb 'Enable', the resource 'campaign', and the specific effect 'sets status=ENABLED'. This clearly distinguishes it from the sibling tool 'pause_campaign', which performs the opposite action.

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 the tool should be used on paused campaigns by saying 'Enable a paused campaign', but does not explicitly state when not to use it or mention alternatives beyond the sibling tool names.

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 full behavioral disclosure. The verb 'List' strongly indicates a read-only operation, and the description mentions the return fields, which is helpful. However, it does not explicitly state that the tool is non-destructive, requires no special permissions, or has any rate limits or pagination. The transparency is adequate but not thorough.

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 a single sentence that is front-loaded and contains no extraneous words. Every part contributes to understanding the tool's purpose. It is highly concise.

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 tool has a simple interface (one optional parameter) and an output schema, so the description doesn't need to detail return values. It mentions some output fields, which is good. However, it does not specify how the optional customer_id affects the query (e.g., whether omitting it uses the default customer) or any limitations (e.g., maximum results). The completeness is adequate for a basic list tool but lacks some important 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?

The input schema has one parameter (customer_id) with 0% description coverage, meaning the schema provides no semantic info. The description does not mention customer_id at all, failing to explain its purpose, format, or behavior (e.g., whether it defaults to the authenticated user). Since schema coverage is low, the description must compensate but does not, resulting in poor parameter semantics.

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 uses a specific verb 'List' and clearly identifies the resource ('campaigns for a Google Ads customer') and the returned data ('status, budget, and core metrics'). This sharply distinguishes it from sibling tools like pause_campaign or add_negative_keywords, which operate on different resources or perform mutations.

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 that the tool is for retrieving campaign data, but it does not provide explicit guidance on when to use it versus alternatives (e.g., 'Use this before modifying campaigns') or when not to use it. The context is clear because sibling tools are mutation-focused, but the description lacks explicit usage instructions.

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 provided, the description carries the full burden of behavioral disclosure. It only states the purpose without revealing behavioral traits such as read-only nature, rate limits, data freshness, or what happens when no data matches filters.

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 a single, front-loaded sentence with no wasted words, making it highly concise and easy to parse.

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 optional parameters, output schema exists), the description covers the basic purpose but lacks detail on filtering behavior and the nature of the output, leaving gaps for an agent to fully understand invocation 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?

Schema description coverage is 0% and the description only explains the 'days' parameter via 'lookback window', leaving 'campaign_id' and 'customer_id' unexplained. This adds value for one of three parameters but is insufficient.

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 'Return', the resource 'search-term performance', and the context 'for the given lookback window', distinguishing it from sibling tools which are actions like pause_campaign or other data retrieval like get_campaigns.

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 when search-term performance data is needed but does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention 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 full burden. It discloses the status change to PAUSED, but does not mention reversibility, immediate effects on ads, prerequisites (e.g., campaign must be active), or other behavioral traits.

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 extremely concise (one sentence, 8 words) and front-loads the core action. Every word is earned, but it could be slightly more informative without losing conciseness.

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?

Despite having an output schema and simple purpose, the description lacks usage guidelines, parameter explanations, and behavioral context. For a tool with no annotations and low schema coverage, it is incomplete.

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%, meaning the description adds no information about parameters. The input schema has campaign_id (required) and optional customer_id, but the description only implies campaign_id. It does not explain customer_id or any constraints.

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 'Pause a campaign' and specifies the exact effect 'sets status=PAUSED'. This distinguishes it from sibling tools like enable_campaign and provides a clear, specific verb+resource definition.

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 does not explicitly state when to use this tool versus alternatives. The name and effect imply pausing a campaign, and the sibling enable_campaign provides contrast, but no when-not or alternative tool guidance is given.

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 full burden. It discloses the unit conversion but does not mention immediate application, budget limits, idempotency, or side effects. More behavioral details are needed for a 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?

Single sentence with no wasted words. It efficiently conveys the core action and unit conversion. Could include additional context without losing conciseness.

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 3 parameters, 0% schema coverage, and no annotations, the description is insufficient. It lacks details on budget constraints, immediate effect, and behavior when campaign is paused. Output schema exists but does not compensate for missing behavioral 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?

Schema description coverage is 0%, so description must compensate. It explains new_budget_dollars is in dollars and converted to micros, adding value. However, campaign_id and customer_id are not explained; customer_id is optional with default null but purpose is unclear.

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 'Set a campaign's daily budget' with the verb 'set' and resource 'campaign's daily budget'. It also explains the unit conversion from dollars to micros. However, it does not differentiate from sibling tools like pause_campaign or enable_campaign, though they are distinct actions.

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. It does not mention prerequisites (e.g., campaign must exist) or when not to use it. Sibling tools are for different actions (pausing, enabling, adding keywords), but no explicit comparison.

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