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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action without detailing side effects, required permissions, reversibility, or what happens if the ad set is not paused. This is a significant gap 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?

The description is a single, front-loaded sentence with no filler. For a tool with one parameter and no output schema, this 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?

The description is minimal and lacks behavioral context (no permissions, side effects, or error scenarios). Given no annotations, it is incomplete for an agent to fully understand the operation's implications.

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 100% (adSetId is described in the schema). The description adds no extra meaning to the parameter, so the baseline of 3 is appropriate.

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 'Activate a paused ad set' uses a specific verb and resource, clearly distinguishing it from sibling tools like pauseAdSet. It directly states what the tool does.

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 usage is implied by the action—activate a paused ad set—but there is no explicit guidance on when to use it vs. alternatives or any prerequisites. No exclusions or alternative routing is mentioned.

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 disclosing behavioral traits. It states the action but does not describe preconditions (e.g., whether the campaign must be paused), side effects, permission requirements, or what happens if the campaign is already active. The 'paused' qualifier implies a precondition but does not elaborate on failure behavior. This is insufficient 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?

The description is a single concise sentence with no fluff, making it easy to parse and front-loaded with the action. However, it is so minimal that it omits critical usage and behavioral details, which slightly reduces the score. It earns its place but could be more informative without becoming verbose.

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 one parameter, no output schema, and no annotations, the description is minimally adequate. It does state the intended target ('paused campaign'), which hints at a precondition. However, it fails to mention what happens when the campaign is not paused, any side effects, or how it differs from bulk activation. Given the simplicity, this is a moderate gap rather than a severe one.

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 schema covers the single parameter with a description 'Campaign ID to activate' at 100% coverage. The tool description adds no additional meaning beyond what the schema already provides. Since schema coverage is high, the baseline is 3, and the description neither improves nor detracts from parameter understanding.

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 ('Activate') and the resource ('a paused campaign'), which is specific and not a tautology. It distinguishes from bulk operations by using the singular 'a', though it does not explicitly name alternatives like bulkActivateCampaigns. The purpose is clear and 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 provides no guidance on when to use this tool versus its siblings. It does not mention that this is for a single campaign as opposed to bulkActivateCampaigns, nor does it explain the difference from pauseCampaign. There are no explicit when-to-use or when-not-to-use instructions, leaving the agent to infer.

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 disclosure burden. It transparently states that activating is the action and that dry-run previews changes, which is useful. It does not cover failure behavior, partial success, or reversibility, so it is only partially transparent.

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?

Two short sentences with no wasted words; the core purpose is front-loaded and the dry-run capability is added as a useful second sentence.

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 two-parameter bulk mutation with no annotations or output schema, the description gives the essential what and the dry-run mode, but omits return shape, partial-failure semantics, and any side effects beyond activation. This is adequate but not 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 100%, so the input schema already documents campaignIds and dryRun fully. The description only restates the dry-run concept without adding format or edge-case meaning, meeting the baseline but not exceeding it.

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 ('Activate') with a plural resource ('multiple campaigns') and states the batch nature, clearly distinguishing it from the singular sibling activateCampaign. This is 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 phrase 'in a single operation' implies this tool is for bulk activation rather than the singular activateCampaign, and the dry-run mention gives a concrete use case. However, it does not explicitly state when to prefer alternatives or when not to use it.

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 confirms the pause action and mentions dry-run preview, but it does not state whether the operation is reversible, what happens on partial failure, or what the response contains. For a mutation tool, this is a significant gap.

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 efficient sentence that front-loads the action and resource ('Pause multiple campaigns') and then notes the dry-run capability. Every phrase earns its place without wasted 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?

This is a bulk mutation tool with no annotations and no output schema, so the description should explain operational context such as return behavior, error handling, or reversibility. The current description covers the basic action and dry-run, but leaves an agent uncertain about the outcome of executing the pause.

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 already documents both parameters: campaignIds as an array of campaign IDs and dryRun as a boolean with default false. The description adds only the idea of 'dry-run mode to preview changes,' which overlaps with the schema's dryRun property without adding new meaning.

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 a specific verb and resource: 'Pause multiple campaigns in a single operation.' It clearly differentiates from the sibling pauseCampaign by emphasizing batch behavior, so an agent can distinguish it without inspecting the schema.

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 phrase 'multiple campaigns' implies the batch use case, and the sibling list includes pauseCampaign as a likely single-campaign alternative. However, the description does not explicitly say when to prefer this tool over pauseCampaign or mention bulkActivateCampaigns as the inverse operation.

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 burden of conveying safety and behavior. 'Check' and 'Identifies' imply a read-only diagnostic operation, and 'configurable thresholds' adds useful behavioral context. However, it does not explicitly state that no changes are made, what the response contains, or how alerts are presented.

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 two focused sentences with no filler. The first sentence states the main action, and the second provides concrete alert examples, so each sentence earns its place.

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 five-parameter tool with no annotations and no output schema, the description is adequate but not fully complete. It does not mention the return shape, empty-alert behavior, or when to prefer this over sibling insight tools, though the schema fully documents parameters and defaults.

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 100%, and each parameter already has clear descriptions with defaults and units. The description adds only the conceptual notion of configurable thresholds and alert categories, not additional semantic detail beyond the schema, so the baseline of 3 applies.

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 a specific verb and resource: 'Check campaigns for performance alerts' and names concrete alert categories like high CPR and low CTR. It is unambiguous about what the tool does, though it does not explicitly distinguish itself from sibling analytics tools such as getInsights.

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?

There is no guidance on when to use this tool versus alternatives like getInsights or compareTwoPeriods. The description implies a threshold-based alert use case but provides no exclusions, prerequisites, or selection criteria.

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 carry behavioral disclosure. It does state the core effect: copying targeting, budget, and configuration. But it does not disclose whether the source remains unchanged, whether the new ad set is active or paused, or what response/errors to expect.

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 efficient sentence, front-loaded with the action and object, and includes the most relevant qualifier about target campaigns without repeating schema details.

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 low-complexity three-parameter tool with full schema coverage, the description provides sufficient context to choose and invoke it correctly. The main gap is the absence of return-value or side-effect details, but this is minor given the simplicity of the operation.

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 100%, so the schema already documents all parameter semantics. The description adds general context about what is copied but no parameter-specific details 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 states a specific action ('Clone') and resource ('an existing ad set'), and clarifies target scope ('same or different campaign'). This clearly distinguishes it from sibling cloneCampaign and other ad-set 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?

The description implies when to use the tool—whenever an ad set needs to be duplicated—and adds useful context about the target campaign. However, it does not explicitly name alternatives such as cloneCampaign or updateAdSet, nor does it state when not to use this tool.

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 carry the burden. It indicates cloning creates new entities but does not disclose potential side effects, such as whether it duplicates budgets or requires specific permissions. It does not mention reversibility or errors that might occur.

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, with only two sentences, and front-loads the primary purpose. It is efficient and free of fluff, though it could be slightly more detailed without becoming verbose.

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 moderate complexity (4 parameters) and lack of annotations or output schema, the description is incomplete. It does not explain what happens to the budget adjustment (e.g., is it applied to the new campaign?), nor does it clarify the behavior of copyAdSets when set to false. Missing details about the expected outcome (e.g., response format, new campaign ID) would leave an agent uncertain.

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 100% for all 4 parameters, so the baseline is 3. The description adds context for the overall purpose but does not elaborate on parameters beyond what's in the schema. It adds minimal extra value for 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 clearly states the action (clone), the resource (campaign), and the scope (optionally clone ad sets). It distinguishes itself from siblings like cloneAdSet by focusing on campaigns. It is specific and 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?

It mentions it is useful for duplicating successful campaign structures, which implies a common use case. However, it does not explicitly say when NOT to use it or contrast with cloneAdSet, which is a close sibling. There is no mention of prerequisites like permissions.

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 adds useful details: the backward-compatible default metrics, result mode options, legacy preset string normalization, and the campaign-specific baseline explanation. However, it does not state whether the operation is read-only, how errors are handled, or what the general response structure looks like for non-campaign levels. Some transparency is present but not comprehensive.

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, well-organized paragraph that front-loads the core purpose. It progressively covers periods, result selection, metrics, and campaign-specific output. Every sentence contributes new information; there is no filler. It could be broken into bullets, but the flow is logical 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?

This is a complex tool with nested period objects, multiple modes, and a specific campaign baseline feature. The description thoroughly covers input selection and the campaign output nuance, but it does not describe the general response format (e.g., metric comparisons, percentage changes) for account, adset, or ad levels. With no output schema, this gap could leave an agent uncertain about the return structure. Adequate 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 coverage is 86%, which is high, so the baseline is 3. The description reiterates most parameter information already present in the schema (e.g., preset vs. timeRange, metrics options, resultMode). It adds minor clarifications like 'legacy preset strings are still accepted and normalized' and the backward-compatible default, but these are also implied in the schema defaults. The description adds little beyond what the schema provides.

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 ('Compare'), names the resource ('performance metrics'), and defines scope ('between two explicit periods for an account, campaign, adset, or ad'). This clearly distinguishes it from siblings like getInsights (single-period) and other ad management tools. The tool's unique purpose is 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 clearly states the tool is for comparing two periods, which implies its use case. However, it does not explicitly mention alternatives or when not to use it (e.g., 'use getInsights for single-period analysis'). No exclusions are given, but the context is clear enough for an agent to infer when it applies.

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, but it only restates that the tool 'creates' a schedule. It does not mention side effects, whether the schedule replaces an existing one, idempotency, validation constraints, or what happens on conflict.

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 redundant flufftons. It is front-loaded with the core action and resource, but 'specific time window' is somewhat vague and could be more precise without adding length.

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 mutation tool with five required parameters, no annotations, and no output schema, the description is too sparse. It omits behavioral context, return value expectations, and parameter constraints such as timeStart needing to precede timeEnd, making it insufficient for confident 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 description coverage is 100%, so all five parameters already have semantic descriptions in the schema. The tool description only adds the vague phrase 'specific time window', which loosely maps to timeStart/timeEnd but provides no additional meaning beyond what the schema already states.

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 action 'Create' and the resource 'budget schedule for a campaign', which is distinct from the sibling tools like updateCampaign or pauseCampaign. It adds 'with a specific time window', giving some scope. However, it does not explicitly differentiate from closely related budget operations or explain what a budget schedule entails.

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?

There is no guidance on when to use this tool versus alternatives such as updateCampaign or cloneCampaign. No prerequisites, conditions, or exclusions are mentioned, leaving the agent to infer appropriate usage solely from the tool name.

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 burden of behavioral disclosure. It explicitly mentions that results are cached for 5 minutes, which is valuable operational context, and the 'Discover'/'Returns' language implies a non-destructive read operation. It does not discuss errors or rate limits, but for a zero-parameter read tool the disclosure is reasonably complete.

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 two sentences with no wasted words. The purpose is front-loaded, the return contents are summarized, and the caching behavior is a single relevant note. Every sentence contributes useful 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?

For a parameterless discovery tool with no output schema, the description adequately covers what the agent needs to know: what to call it for, what it returns, and the caching caveat. It does not describe the response structure or pagination, but that is a minor gap given the tool's simplicity.

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 tool has zero parameters, so the schema is trivially complete with 100% coverage. The description still adds useful context by identifying the System User Token as the implicit authorization scope, which is appropriate at the baseline level for parameterless tools.

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 a specific verb ('Discover') and resource ('all ad accounts accessible via the System User Token'), and lists the returned data (IDs, names, business information). It is clear and easily distinguishable from siblings like getAccountInfo, though it does not explicitly name any alternative.

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 when an agent needs to enumerate all ad accounts available to the System User Token, but it does not explicitly state when to use it over alternatives or when not to use it. Usage context is present through the word 'Discover' and the scope phrasing, but no exclusions or sibling comparisons are 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 the behavior disclosure burden. 'Get' clearly signals a read-only operation and the listed fields imply the response content, but no details are given about permissions, error conditions, data freshness, or any side effects. This is adequate for a simple getter but not rich.

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. It begins with the action and resource, then lists the useful detail categories, making it immediately scannable for an agent.

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?

This is a low-complexity, single-parameter read tool with no output schema. The description names the main output areas—currency, timezone, status, and linked business—which is enough for an agent to anticipate the return value. It lacks usage-alternative context, but that is partially addressed elsewhere in this evaluation.

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 100% coverage, documenting accountId as an ad account ID in act_XXX format. The description adds no additional parameter semantics, but the schema already fully explains the required input, so the baseline of 3 is appropriate.

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 a specific verb and resource: 'Get detailed information about an ad account' and names concrete data categories: currency, timezone, status, and linked business. It is clear, though it does not explicitly distinguish itself from siblings like getBillingInfo or discoverAdAccounts.

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?

There is no guidance about when to use this tool versus alternatives. No mention of when to prefer getAccountInfo over getBillingInfo or discoverAdAccounts, and no exclusions or prerequisites are stated.

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 basic operation without revealing whether it is read-only, whether pagination exists, or what the response format looks like. This is a significant gap for an unannotated 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 a single, concise sentence with no wasted words. The core action is front-loaded, making it efficient 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 tool's simplicity (one parameter, no output schema), the description adequately conveys its purpose. However, it lacks any detail on the return structure or potential edge cases (e.g., empty results), which is a minor gap for an unannotated tool. Overall, it is reasonably complete for the intended use.

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 schema already provides a full description for the single parameter adId (100% schema coverage). The tool description adds no extra semantic detail beyond what the schema states, so it meets the baseline but provides no additional value.

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 a specific verb ('Get') and resource ('creatives') tied to an ad, which distinguishes it from sibling tools like getAds or getCampaigns. It leaves no ambiguity about what the tool retrieves.

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 for fetching creatives for a specific ad, which is evident from both the name and content. However, it does not explicitly mention when to avoid using it or name alternatives, though the sibling list makes the context clear. No exclusions are provided, so it falls short of a 5.

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 present, so the description carries the burden of behavioral context. 'Get' strongly implies a read-only operation and the listed fields signal the returned data, but the description does not explicitly state that the tool makes no changes or explain how 'issues' are represented.

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 filler: the verb, resource, and key output fields are all present. Every word contributes.

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?

With one required parameter and no output schema, the description is mostly sufficient for invoking the tool, and it names three key return components. However, 'full ad details' and 'issues' remain vague, and the lack of any output schema or behavioral notes leaves some ambiguity about the exact response shape.

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 schema already covers the only parameter (adId with 'Ad ID'), so the baseline is 3. The description does not add format details, examples, or constraints for adId, but it does connect the parameter to the detailed results returned.

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 operation ('Get') and resource ('full ad details') and names specific returned fields (effective status, creative ID, issues). It does not explicitly differentiate from siblings like getAds or getAdCreatives, but the singular adId and 'full details' wording make the intended use reasonably clear.

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?

Usage is implied: call this when you have an adId and need detailed information about a specific ad. However, it does not state when not to use it or mention alternatives such as getAds for listing ads or getAdCreatives for creative content.

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 of behavioral disclosure. It discloses the status filtering behavior but does not state that the operation is read-only, whether pagination or limits apply, or what happens if neither adSetId nor campaignId is provided. These gaps are significant for a tool with no annotation safety net.

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?

Two short sentences with no filler. The core action and the optional filter are both presented up front, and every word earns its place.

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 list-type tool with fully documented parameters, the description is largely sufficient: it names the resource, the two scopes, and the filter. The absence of an output schema or mention of return shape is a minor gap, but the tool's behavior is straightforward enough that an agent can call it correctly with the provided 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 100%, so the schema fully documents all three parameters. The description adds minimal meaning beyond the schema: it reinforces that ads can be fetched 'from an ad set or campaign' and that status filtering is supported. This matches the baseline of 3 because the schema is doing the heavy lifting.

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 a specific verb and resource: 'Get ads from an ad set or campaign.' It clearly indicates the tool's function and the two valid scopes. It does not explicitly differentiate itself from siblings like getAdDetails or getAdSets, so it stops short of a 5.

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 when to use the tool: when you need ads from an ad set or campaign, optionally filtered by status. It offers no explicit guidance on when to prefer getAds over getAdDetails or getAdSets, and no exclusions or alternatives are named. This is adequate but relies on inference.

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 behavioral burden. 'Get' indicates a read-only operation, and the named fields suggest return content, but the description does not disclose response shape, error behavior, or access requirements.

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: verb, resource, and example fields. There is no unnecessary wording or filler, making it easy to parse quickly.

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 one-parameter read tool, the core invocation is clear. However, with no output schema and no mention of alternatives, the response structure remains ambiguous and the tool is not explicitly positioned relative to siblings like getAdSets.

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 single parameter adSetId is already fully described in the input schema, so the description adds no new parameter-level detail. It does provide mild context that the ID is for fetching extended ad set details, but no format or source 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 clearly states the verb ('get'), resource ('ad set details'), and the word 'extended' with example fields. This distinguishes it from list-oriented siblings like getAdSets, though it does not explicitly name that sibling.

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 phrase 'extended ad set details' implies this is for deeper inspection of a single ad set, but the description does not explicitly state when to choose this tool over getAdSets or other detail tools. Usage context is inferred rather than explicit.

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 must carry the full burden of behavioral disclosure. It simply says 'Get', implying read-only, but it does not state whether the operation is safe, non-destructive, or whether there are any side effects. It also fails to explain what happens when both accountId and campaignId are provided, or when neither is provided. The behavior around missing parameters and potential pagination is undocumented, leaving the agent uncertain about the tool's behavior.

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 with two clauses, conveying the essential action and a key feature. It is front-loaded with the primary purpose and contains no filler or redundant details. Every word earns its place, making it highly concise 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?

For a three-parameter tool with no annotations and no output schema, the description is too sparse. It does not clarify the relationship between accountId and campaignId (e.g., mutual exclusivity or precedence), nor does it mention pagination, response shape, or any error conditions. An agent needs more context on how to properly invoke this tool and interpret results, but the description leaves these gaps.

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 already provides descriptions for all three parameters with 100% coverage, so the baseline is 3. The description adds the phrase 'supports filtering by status', which is redundant since the schema already specifies the status enum and default. It also rephrases 'from a campaign or account' which is already captured by the parameter descriptions. No additional meaning is added 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 states a specific verb ('Get') and resource ('ad sets') plus scope ('from a campaign or account'). It clearly indicates a list retrieval operation. However, it does not explicitly distinguish itself from sibling tools like getAdSetDetails or getAds, which could be confused with the same resource. The intent is clear but not fully differentiated from close siblings.

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 for retrieving ad sets at the campaign or account level, but it gives no explicit guidance on when to prefer this tool over alternatives like getCampaigns or getAdSetDetails. There is no mention of exclusions or when not to use it, so the agent must infer usage from the name and context. This is implied rather than explicit.

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 burden of behavioral disclosure. It mentions that monetary values are in the smallest currency unit, which is useful for interpreting output. However, it does not disclose whether this is a read-only operation, any data limits, or response format details. This is adequate for a read-like tool but not fully transparent.

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, two sentences, with the core function front-loaded. The currency unit note is valuable and placed at the end. There is minimal waste, though the second sentence could be seen as extra, but it earns its place for interpretability.

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 simplicity (single parameter, no output schema), the description is complete enough. It lists the included fields, which compensates for the lack of an output schema. The only omission is potential authentication requirements, but for a billing read tool, it's reasonably 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 schema already documents the parameter fully (accountId as string with description 'Ad account ID (act_XXX) or account name'), and schema coverage is 100%. The description adds no additional parameter semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

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: retrieving billing and financial information for an ad account, listing specific data fields such as pending balance, total spend, spend cap, payment method details, and tax info. It distinguishes itself from sibling tools like getAccountInfo by focusing on billing-specific details.

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 billing information is needed, but it does not explicitly state when not to use this tool or mention alternatives. For example, it doesn't clarify that getAccountInfo might be more appropriate for general account details. The context is clear for billing purposes, but lacks explicit 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. The description only lists returned fields but does not state whether the operation is read-only, whether special permissions are required, error handling (e.g., campaign not found), or any side effects. For a tool that likely performs a read, this omission is significant.

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 zero filler. It immediately states the action and the specific information returned. Every word earns its place.

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 single required parameter and no output schema. The description lists the key fields returned, which gives some context, but it omits behavioral details (permissions, errors, pagination if any) and does not explain the difference from getCampaigns. Given the simplicity, it is adequate but not complete; more context on when to use and expected behavior would improve it.

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 100%: the only parameter campaignId is described as 'Campaign ID' in the schema. The description does not add any additional meaning, format, or constraints beyond that. Since the schema fully documents the parameter, baseline 3 is appropriate.

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: 'Get extended campaign details' and enumerates specific fields (bid strategy, buying type, special ad categories, issues). This is a specific verb+resource combination and distinguishes it from the sibling getCampaigns (likely basic listing) by the word 'extended' and the listed details.

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 for retrieving extended campaign details but does not explicitly contrast with getCampaigns or any alternative. There is no 'use this instead of X' guidance. The intended context is inferable from the 'extended' qualifier, but explicit exclusion or alternative routing is absent.

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 exist, so the description must carry behavioral disclosure. It reveals that filtering by status is supported and account can be an ID or name, but it doesn't disclose return shape, pagination, ordering, or the fact that this is a read-only operation (beyond the verb 'Get').

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?

Two tight sentences, no redundant phrasing, and the core action is front-loaded. 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 schema handles parameter semantics, but the description omits any indication of return format or whether results are paginated, and it doesn't situate this tool against the many campaign siblings. For a simple list operation this is a minor but real gap.

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?

Input schema already documents both parameters including enum values and the act_XXX/name forms; the description mostly restates these facts without adding new semantic detail. Baseline 3 applies given 100% schema coverage.

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?

States a specific operation (Get campaigns from an ad account) and includes filtering and account-specification details. It is clearly a list-level tool, but it doesn't explicitly contrast itself with getCampaignDetails or other siblings, so it stops short of full differentiation.

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 choose this over getCampaignDetails, which likely retrieves a single campaign, or over other campaign management tools. The description only states what it does, not when it should be preferred.

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 — and it delivers: it discloses the return-shape difference between account level (aggregated summary) and campaign/adset/ad levels (per-item metrics with normalized ids/names, spend, results, CPR). It does not cover pagination or error behavior, but the structural disclosure is strong for a metrics 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?

Two focused sentences with no filler. The core capability and supported levels are front-loaded, and the return-shape clarification is appended where it belongs. Could be tightened slightly but is appropriately sized.

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?

With no output schema, the description must explain return values — it does, clarifying the aggregated vs per-item distinction and listing the metric fields. For a read-only metrics tool with well-documented parameters, the remaining gaps (pagination, max range limits) are minor.

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 100% with detailed parameter descriptions (enum values, format hints, precedence between timeRange and datePreset). The description adds real value beyond the schema by explaining what each level actually returns, which is the most ambiguous part of the contract.

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 clear verb+resource ('Get performance metrics for accounts, campaigns, adsets, or ads') and distinguishes levels of aggregation. It does not explicitly name sibling tools to differentiate from, but the purpose is specific enough to separate it from discovery tools like getCampaigns/getAdSets.

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?

Usage context is implied rather than stated: the description tells what it returns but never says when to choose this over getCampaignDetails, getAdSetDetails, or compareTwoPeriods. With 30 siblings, explicit routing guidance would materially help an agent pick correctly.

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 must carry the behavioral burden. 'Get' and 'suggestions' imply a read-only operation, and the seed-interest dependency is clear arranged. However, it does not mention authentication requirements, rate limits, failure modes, or output characteristics, so the disclosure is minimal but not contradictory.

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 filler. It is efficient, though it sacrifices a small amount of helpful context that could have been added, such as naming the closest sibling tool.

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 two-parameter tool with fully documented parameters, the description covers the core invocation. However, the lack of annotations and output schema means the return shape, success/failure behavior, and any additional constraints are unstated, leaving some reliance on the tool name and general inference.

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 100%, so the description does not need to add parameter detail. It reinforces that interestList acts as 'seed' interests, but adds no new meaning beyond the schema and does not clarify limit behavior beyond the schema default.

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 names a concrete action ('Get') and resource ('interest suggestions') and ties the output to seed interests. This is enough to distinguish it from sibling searchInterests at a basic level, though it does not explicitly name alternatives.

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?

There is no explicit guidance on when to use this tool versus a sibling like searchInterests or validateInterests. The phrase 'based on a list of seed interests' implies an input condition but does not state a use case or when not to use this tool.

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 of behavioral disclosure. The description only states the action without revealing side effects, such as whether pausing affects related ads, whether the action is reversible, or what the response looks like. For a mutating operation, this is a significant gap.

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, efficient sentence with no wasted words. It front-loads the action and the object.

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 single-parameter tool, the schema covers the parameter fully. However, the description lacks any behavioral context (what happens after pausing, reversibility, effect on ads) and has no output schema, so an agent may not fully understand the consequences of calling this tool.

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 100% and there is a single parameter (adSetId) that is already well-documented in the schema as 'Ad set ID to pause'. The description adds no additional meaning beyond the schema, so the baseline of 3 applies.

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 a clear verb and resource: 'Pause an active ad set'. It clearly distinguishes the action from sibling tools like pauseCampaign (pauses a campaign) and activateAdSet (activates rather than pauses). However, it doesn't explicitly differentiate itself from the sibling tools, so a 4 rather than 5.

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 is given on when to use this tool versus alternatives such as pauseCampaign or bulkPauseCampaigns. The description does not state prerequisites (e.g., the ad set must currently be active) or mention any scenarios where another tool would be more 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?

There are no annotations, so the description must disclose behavioral context on its own. It only restates the state change implied by the name and says nothing about reversibility, downstream effects on ads or budgets, idempotency, or required permissions.

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 short sentence with no filler and front-loads the action. It is concise but minimal, leaving out behavioral context that could have been added without bloating the text.

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 one-parameter mutation with no annotations or output schema, the description conveys the basic operation. It omits any indication of what pausing entails or how it differs from the bulk variant, making it minimally adequate rather than 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 already documents campaignId as 'Campaign ID to pause' with 100% coverage. The description adds no additional parameter meaning, so it merits the baseline of 3.

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 the imperative 'Pause' with the resource 'an active campaign,' making the action unambiguous. However, it does not explicitly differentiate from sibling tools like bulkPauseCampaigns or pauseAdSet beyond the name itself.

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 is given about when to choose this tool over alternatives such as bulkPauseCampaigns, activateCampaign, or updateCampaign. Agents must infer usage purely from the tool name and sibling list.

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 indicates a search (likely read-only), but does not disclose pagination behavior, result format, authentication needs, or any constraints around the search.

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 concise sentence with no filler and the core purpose is front-loaded. It is efficient, though slightly sparse in supporting context.

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 tool with one optional parameter, the description is minimally adequate. However, with no output schema and no annotations, it does not explain what the search returns or how results are presented, leaving some ambiguity for an agent.

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 100%, and the 'limit' parameter is already fully documented in the schema. The description adds no extra meaning about the parameter, so it sits at the baseline for schema-documented parameters.

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 a specific verb ('Search') and a distinct resource ('Facebook behavior targeting categories'). It is easy to understand what the tool does, though it does not explicitly differentiate itself from sibling tools like searchInterests or searchDemographics.

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 is provided about when to use this tool versus the many sibling search tools. The name and description imply it is for behavior targeting, but there are no explicit when-to-use or alternative-selection cues.

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 indicates a search/read operation but does not mention output format, pagination behavior, or any constraints on the search results. This is a notable gap for a tool with no annotation safety signals.

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, focused sentence with no filler or repetition. It front-loads the core action and resource while leaving parameter details to the schema, which 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?

For a simple two-parameter search tool with full schema coverage, the description is minimally adequate. However, with no output schema or annotations, it could benefit from mentioning whether results are lists, how pagination works via the limit parameter, or how this relates to sibling search tools.

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 100%, so the baseline is 3. The description's phrase 'by class' aligns with the demographicClass parameter, but it adds no new semantic detail beyond what the schema enum and parameter descriptions already provide.

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 ('Search') and a clear resource ('Facebook demographic targeting categories') with a scoping qualifier ('by class'). This distinguishes it from sibling search tools like searchInterests, searchBehaviors, and searchGeoLocations based on the targeting category type.

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 when to use the tool: when the agent needs Facebook demographic targeting categories. However, it provides no explicit when-not-to-use guidance or references to alternative sibling tools, leaving the agent to infer usage from the name and resource.

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 of behavioral disclosure. It only states that the tool searches and for what purpose; it does not describe the return shape, matching behavior, result limits, or any other operational characteristics.

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 filler. The core action and resource are front-loaded, and the parenthetical examples add useful context without bloating the text.

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?

This is a simple tool with well-documented parameters, so an agent can call it with the required query. However, with no output schema and no behavioral details in the description, the agent is left without expectations about what results look like or how matching works.

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 100%, so the baseline is 3; the schema already explains query, limit, and locationTypes. The description adds only illustrative examples of location types and does not provide meaningful parameter detail beyond what the schema gives.

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 ('Search') and resource ('geographic locations') with concrete examples ('countries, cities, regions'), making the tool's purpose clear. It is implicitly distinguished from sibling interest/behavior/demographic search tools, though it does not name them explicitly.

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 phrase 'for targeting' gives useful context about when to use the tool. However, it does not explicitly mention alternative tools like searchInterests, searchBehaviors, or searchDemographics, nor does it state exclusions or when not to use this tool.

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 of behavioral disclosure. It does not mention whether the operation is read-only, pagination behavior, rate limits, or what the response format looks like. The simple search implies a safe read, but that is not explicitly stated.

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 concise sentence, front-loaded with the action and resource. It is appropriately sized, though 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?

For a tool with two parameters and no output schema, the description is incomplete. It lacks usage guidance and behavioral context, and the agent receives no hints about what the search returns or how to distinguish it from similar search tools.

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 100%, so the baseline is 3. The description adds minimal value by saying 'by keyword', which essentially restates the query parameter's schema description. No additional semantic context is provided.

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 a specific action ('Search') and a specific resource ('Facebook interest targeting options'), which is clear and not a tautology. It distinguishes from siblings like searchBehaviors and searchDemographics by focusing on interests, though it doesn't explicitly name any alternatives.

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 is provided on when to use this tool versus related siblings like getInterestSuggestions or validateInterests. The description only states what it does, not the appropriate context 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?

No annotations are provided, so the description must carry the full burden. It discloses that the tool mutates an ad, but not whether status changes are immediate, whether bid changes affect running delivery, whether the operation is idempotent, or what permissions are required. The use of 'or' is also ambiguous about whether both status and bidAmount can be updated together.

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 filler or redundant content. It is economical and immediately communicates the tool's core action, though the 'or' phrasing introduces a slight ambiguity.

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 three-parameter update tool with a fully documented schema, the one-line description plus schema is enough to construct a valid call. However, with many sibling tools and no annotations or output schema, the description lacks routing guidance and does not fully explain behavioral expectations.

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 100%, with adId, status enum, and bidAmount in cents already documented. The description adds no parameter-level detail beyond the schema, so it meets but does not exceed the baseline.

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 operation ('Update'), the resource ('an existing ad'), and the specific fields involved ('status or bid amount'). It is distinguishable from siblings like updateAdSet and updateCampaign by naming the ad resource, though it does not explicitly contrast with them.

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?

There is no guidance on when to use this tool versus related siblings such as pauseCampaign, activateCampaign, updateAdSet, or pauseAdSet. The intended usage is only implied by the tool name and description, with no exclusions, prerequisites, or alternatives mentioned.

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 must carry the behavioral disclosure burden. It does disclose the key trait that only provided fields are updated, implying a partial update (PATCH-like). However, it omits other relevant behaviors such as permissions required, atomicity, or return format. This is a minimal but non-contradictory disclosure.

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, direct sentence with no wasted words. The primary action is front-loaded, and the partial-update note is appended efficiently. It is an exemplar of concise, structured communication.

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 6 parameters, including a nested targeting object, the description is minimal but not incomplete. The schema covers parameter details, and the description adds the core behavior. However, it lacks usage context and does not mention return values (no output schema), so it is adequate but not richly 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 100% parameter coverage, describing each field individually. The description adds crucial semantics beyond the schema by clarifying that only provided fields are updated, which defines how the optional parameters behave. This enriches the agent's understanding of parameter interactions.

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 'Update' and resource 'existing ad set', making the purpose unambiguous. It distinguishes from status-specific siblings like pauseAdSet and activateAdSet, though it does not explicitly contrast them. The name itself is self-explanatory, reinforcing clarity.

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 no guidance on when to use this tool versus alternatives. It does not mention that dedicated tools exist for status changes (pause/activate) or that this tool is for general field updates. An agent would have to infer the appropriate usage from the name alone.

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 burden of behavioral disclosure. It clearly indicates a mutating operation on an existing campaign and the patching behavior of only updating provided fields. However, it does not disclose return values, permission requirements, or side effects when invalid fields or campaign IDs are supplied.

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 two short sentences with no redundant wording. The primary action is stated first, and the partial-update behavior is added as a concise, useful qualifier.

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 and schema together cover the essential call mechanics: which campaign to update and which fields can change. However, without an output schema or additional context, the agent cannot know the return format, and the description does not address overlap with specialized status-change siblings like pauseCampaign and activateCampaign.

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 100%, so the schema already documents each parameter. The description adds meaningful parameter semantics by stating that only provided fields are updated, which clarifies how optional parameters are applied. This goes beyond what the schema alone states.

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 a clear verb and resource: 'Update an existing campaign.' It also adds 'Only provided fields will be updated,' which clarifies the update scope. However, it does not explicitly differentiate from sibling tools like pauseCampaign or activateCampaign, which also modify campaign state.

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 no guidance on when to use this tool versus alternatives. It does not mention that status-specific operations like pausing or activating might be better handled by dedicated siblings, nor does it state prerequisites or expected usage 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 carries the full burden of behavioral disclosure. It only states the 'at least one' requirement but does not explain what 'validate' means in terms of side effects (e.g., is it read-only?), what happens on invalid inputs, or what the response structure looks like. It also does not clarify whether both lists can be provided simultaneously or how they interact.

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 that states the action, resource, and the critical constraint without any waste. Every word earns its place, and it is immediately scannable.

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 there is no output schema and no annotations, the description is too sparse for an agent to fully understand the tool's behavior. It lacks information about the return value (e.g., does it return a boolean, a list of valid/invalid items?), error handling, or any side effects. For a validation tool, the agent needs to know what to do with the result, and this is missing.

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 schema already describes both parameters clearly ('Interest names to validate' and 'Interest Facebook IDs to validate'), covering 100% of the parameter semantics. The description adds the constraint about at least one being required, which is not in the schema (no required fields), so it does add some value. However, it does not provide additional meaning about the parameters themselves beyond what the schema states.

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 action (validate) and resource (interests) with the method (by name or Facebook ID). This distinguishes it from siblings like searchInterests (which searches/disovers) and getInterestSuggestions (which suggests), 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 mentions the key usage constraint that at least one of the two lists must be provided, which is essential for calling the tool. However, it does not explicitly state when to use this tool versus alternatives like searchInterests, nor does it provide any context about typical validation scenarios or prerequisites. The distinction is implied but not made explicit.

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