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

With no annotations, the description carries the behavioral burden. It discloses the expected statuses (PROCESSING, COMPLETE, FAILED) and the non-obvious callback behavior to download_async_report_tool. It does not specify how to handle FAILED or any rate-limit/retry behavior, which is a minor gap but not a contradiction.

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 compact, front-loaded with the core purpose, and uses bolded directives for the conditional actions. Every sentence adds operational value and none are wasted.

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

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

The description covers the main polling workflow and handoff to the download tool, and an output schema exists for return-value details. The only notable omission is guidance for the FAILED status, but the overall context is sufficient for an agent to invoke the tool correctly.

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

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

Schema description coverage is 0%, so the description must compensate. It only clarifies that task_id should be the same as the one from creation; advertiser_id is never mentioned or explained. The agent would have to infer the meaning and required relationship of advertiser_id from context.

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 ('Checks the status of an async report task') and names the producing tool ('created by create_async_report_tool'). It is easily distinguishable from sibling tools like create_async_report_tool and download_async_report_tool.

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 gives explicit conditional guidance: if PROCESSING, inform the user and check again; if COMPLETE, call download_async_report_tool with the same task_id. This clearly routes the agent between polling and handoff behavior, leaving little to 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?

With no annotations, the description carries the full behavioral burden. It discloses that the tool is asynchronous, returns a task_id, requires progress monitoring, and produces retrievable data only after status COMPLETE. It also provides user-communication expectations. It does not mention failure modes, polling intervals, or task expiration, but the core async behavior is transparently described.

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 dense but purposeful: the first sentence states the core function, the middle provides a clear action sequence, and the end lists critical parameter constraints. The workflow instructions could be more visually structured with line breaks, but every sentence earns its place and the most important info is front-loaded.

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

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

The description covers the async lifecycle well and gives the agent end-to-end instructions, but several required parameters remain semantically opaque (dimensions, metrics, advertiser_id) and no alternative synchronous path is mentioned. Since the output schema exists, the return value is not the main gap; parameter semantics and alternative-tool context are the missing pieces.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaning by enumerating report_type values, data_level values, and the YYYY-MM-DD date format. However, it leaves dimensions, metrics, and advertiser_id underspecified, so the compensation is only partial for a seven-parameter schema with no property descriptions.

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

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

The description opens with a specific verb and resource: 'Creates an async report task for large datasets or long date ranges.' It clearly identifies the tool's role within an async workflow and distinguishes it from sibling tools by naming the follow-up check/download tools. An agent can immediately understand what this tool does and why it exists.

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 gives explicit procedural guidance: call check_async_report_tool immediately with the returned task_id, retrieve data with download_async_report_tool when status is COMPLETE, and inform the user. It also sets a clear usage context ('large datasets or long date ranges'). However, it does not explicitly say when not to use this tool or compare it to get_reports_tool for synchronous reporting.

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 carries the behavioral burden. It clearly indicates a non-destructive download action and reveals the return payload ('report rows'). It does not mention retention windows, size limits, or whether the downloaded data is consumed/one-time, but for a straightforward async download step the transparency is adequate.

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

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

The description is three short, front-loaded lines with no filler. The critical precondition is bolded for visibility, and the return statement is minimal but sufficient.

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

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

Given an output schema, the description covers the main contract: what to call, when to call it, and what it returns. The missing context around advertiser_id and download-specific caveats is minor but keeps this from being fully complete.

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

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

Schema description coverage is 0%, so the description needed to compensate. It clarifies what task_id refers to, but it never explains advertiser_id or how the two IDs relate. The names are fairly self-explanatory and consistent with sibling advertiser-scoped tools, but a clear semantic gap remains.

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 ('downloads') and a clear resource ('completed data for an async report task'), and states the output ('report rows'). It also distinguishes itself from the status-checking sibling check_async_report_tool by framing this as the follow-up data-fetching step.

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 gives an explicit, unambiguous condition: only call after check_async_report_tool returns status COMPLETE. This directly tells the agent when the tool is appropriate and prevents premature calls. No alternative download tool exists among the siblings, so no further exclusions are needed.

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 behavioral burden. It does disclose useful configuration behavior: default dimensions, allowed dimension values, and an objective_type example. However, it omits output behavior, failure/empty cases, time range, and any side effects, which is a meaningful 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?

Compact and front-loaded: the opening sentence states the core purpose, and each subsequent sentence adds a specific usage constraint. No filler, repetition, or unnecessary background.

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 is straightforward and has an output schema, so return-value documentation is less critical. But with no annotations, no alternative guidance, and incomplete parameter coverage (advertiser_id), the description is adequate for a basic call but not fully complete for confident tool selection and 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?

The description adds value by explaining ad_ids (required), dimensions (allowed values and default), and giving an objective_type example, which is important since schema description coverage is 0%. However, it omits advertiser_id, a required parameter, and its claim that 'dimensions defaults to ['PLACEMENT']' conflicts with the schema's `default: null`, creating ambiguity for the agent.

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 verb ('Get'), a concrete resource ('benchmark metrics'), names the exact metrics (CTR, CVR, CPM, CPC), and defines the scope ('for specific ads compared to industry averages'). This clearly separates it from sibling reporting tools like get_reports_tool and get_creative_fatigue_tool.

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

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

Provides practical invocation hints (ad_ids required, dimensions defaults, allowed dimension values, objective_type example), but never explicitly says when to use this tool vs alternatives or when not to. The 'compared to industry averages' framing implies benchmark use, but there are no exclusions or routing to sibling tools.

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 full burden. It does not disclose pagination behavior (implied by page/page_size), the nature of filters, or any side effects (e.g., read-only). The bare statement 'Get ad groups' suggests a safe read operation but lacks critical behavioral context.

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, making it concise. However, it lacks structure (e.g., separate lines for purpose, usage, parameters) and is arguably too terse for a tool with 5 parameters and an output schema.

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 has 5 parameters, nested objects, and an output schema, the description is severely incomplete. It does not explain pagination, filter syntax, campaign constraints, or the structure of the response. The output schema exists but the description should still provide an overview of the return value.

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

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

Schema description coverage is 0%, meaning the input schema provides no parameter descriptions. The description only mentions 'optional filtering' without explaining the `filters` object, `page`, `page_size`, or `campaign_id` parameters. This adds almost no value over the schema itself.

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' and resource 'ad groups', and specifies the scope 'for a specific advertiser' with optional filtering. This distinguishes it from sibling tools like get_ads_tool or get_campaigns_tool, which target different resources.

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

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

No guidance is provided on when to use this tool versus alternatives or what prerequisites are needed. The description only implies use when retrieving ad groups for an advertiser, but fails to mention exclusions or comparisons to siblings.

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

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

With no annotations, the description must convey behavioral traits. It only states the basic action and optional filtering, failing to disclose pagination behavior, the nature of filtering, or any side effects. The tool has parameters for page and page_size, but these are not mentioned.

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

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

The description is a single short sentence, but it sacrifices informativeness for brevity. It fails to provide necessary details about parameters or usage, making it under-specified rather than 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?

Given the complexity of 5 parameters including optional filtering and pagination, the description is woefully incomplete. It lacks guidance on how to construct filters or use pagination, leaving critical gaps that are not filled by the schema or annotations. The presence of an output schema is noted but does not compensate.

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

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

Schema description coverage is 0%, yet the description adds nothing about the five parameters. 'Optional filtering' does not explain how the 'filters' object works, nor does it address page, page_size, or adgroup_id. This leaves agents completely in the dark.

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' and the resource 'ads', constrained to 'a specific advertiser', which precisely identifies the tool's function. This distinguishes it from sibling tools that focus on different resources like ad groups or reports.

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 information on when to use this tool versus alternatives, nor does it mention prerequisites, exclusions, or typical use cases. Given the variety of sibling tools, this omission hinders correct selection.

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 burden of behavioral disclosure. It does state that it returns advertiser_id, balance, credit_limit, and currency for each account, which clarifies the outcome. However, it does not mention read-only behavior, authentication requirements, pagination, possible empty results, or error cases, leaving some behavioral gaps.

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

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

The description is three short, purposeful sentences with no filler. It leads with the tool's purpose, then the return values, then the prerequisite. Every 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 one-parameter getter with an output schema, the description covers the essential context: what it returns é and how to get the required bc_id. It lacks explicit notes on access restrictions or empty results, but those are not critical for this simple read-oriented 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 coverage is 0%, so the description must compensate. It successfully ties the lone parameter bc_id to a Business Center and tells the agent exactly where to get it via get_business_centers_tool. While it does not provide format details, this is sufficient for a single string parameter.

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

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

The description clearly states a specific action ('Get cash balance and credit limit') and a specific resource ('all advertiser accounts within a Business Center'), and it lists the returned fields. This is distinct from sibling tools like get_advertiser_info_tool or get_authorized_ad_accounts_tool because it focuses on balance and credit limit scoped to a Business Center.

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 gives an explicit prerequisite: 'Use get_business_centers_tool first to get bc_id.' This tells the agent how to obtain the required parameter and establishes a clear call order. It does not spell out when not to use this tool, but the context is sufficient for a simple getter.

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. It indicates a read-only metadata operation and adds a meaningful behavioral caveat about timezone dependency, but it does not address permissions, response shape, batch size limits, or error behavior. This is adequate for a simple getter 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?

Two sentences with no wasted words. The first sentence states exactly what the tool does and what it returns; the second explains why it matters. This is an appropriately sized, front-loaded definition.

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 metadata lookup with an output schema, the description is complete. It tells the agent what will be returned, and why the data is important for interpreting other tools. Nothing critical is missing for an agent to decide to call and correctly invoke 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?

The schema has 0% description coverage, but the description compensates by specifying the parameter applies to 'one or more advertisers' and explaining what metadata is retrieved. The parameter 'advertiser_ids' is self-explanatory in context, and the description adds meaning beyond the raw schema by clarifying batch usage.

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 and resource: 'Get account-level metadata' and enumerates the exact fields returned (currency, timezone, industry, status). It also clarifies the tool operates on 'one or more advertisers', which sets it apart from sibling tools focused on campaigns, ads, reports, or business-center assets.

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 gives clear context for when to use this tool: it is 'foundational context for interpreting all other data', specifically noting date breakdowns depend on the account timezone. It does not explicitly name alternatives or state when not to use it, but the guidance is strong enough to route an agent effectively.

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. It discloses the allowlist requirement and the 404 error possibility, which is useful behavioral context. It also lists the return fields (estimated_audience_size_lower, estimated_audience_size_upper, reach_trend). However, it doesn't mention rate limits, pagination, or what happens with invalid targeting criteria. The description adds some value but not rich behavioral detail.

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

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

The description is compact and front-loaded with the core purpose. The additional notes on allowlist access and parameter formats are useful and not redundant. It's a bit dense with multiple notes in one paragraph, but each sentence earns its place. No 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?

The tool has 7 parameters, no annotations, and an output schema exists. The description covers the return fields and two parameter formats, but leaves several parameters unexplained. The allowlist note is important context. For a tool with this complexity, the description is adequate but not complete—an agent might still be unsure about how to format location_ids or interest_category_ids.

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

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

Schema description coverage is 0%, so the description must compensate. It explains objective_type and gender formats, which adds meaning beyond the schema. However, it doesn't explain age, placements, location_ids, interest_category_ids, or advertiser_id. With 7 parameters and only 2 explained, the compensation is partial. Baseline 3 is appropriate because the description does add some value but leaves gaps.

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 estimated audience reach for given targeting criteria.' This is a specific verb ('Get') and resource ('estimated audience reach'), and it distinguishes itself from sibling tools like get_targeting_options_tool (which likely returns targeting options rather than reach estimates). It doesn't explicitly name a sibling, but the purpose is clear enough.

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 some usage context: it notes the endpoint requires allowlist access and gives examples for objective_type and gender. However, it doesn't explicitly state when to use this tool versus alternatives like get_targeting_options_tool or get_reports_tool. The allowlist note is useful but not a full usage guideline.

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, and the description does not disclose any behavioral traits beyond the basic read operation. There is no mention of pagination, rate limits, or authentication 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?

A single sentence that is front-loaded with the key action and resource. No redundant information.

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

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

Given the simple nature of the tool (list ad accounts) and the existence of an output schema, the description is minimally adequate but lacks behavioral transparency and usage context.

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

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

Schema description coverage is 0%; the description does not explain the purpose of the 'random_string' parameter. Although it has a default value and is not required, the description should clarify its use.

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?

Description clearly states verb (Get), resource (authorized ad accounts), and scope (accessible by current access token). It distinguishes itself from sibling tools like get_ad_groups_tool by being specific to ad accounts.

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

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

No guidance on when to use this tool versus alternatives. With many sibling tools, explicit context on when to choose this over others is missing.

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 disclosure burden. It discloses the return fields and the asset_type constraint, adding value beyond the name. However, it does not state whether this is a read-only operation, how invalid asset_type values are handled, or whether results are paginated — a moderate gap given zero annotation coverage.

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?

Four sentences, each earning its place: purpose, constraint, return fields, and prerequisite. The primary action is front-loaded and there is zero filler or redundancy.

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

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

With only two simple required parameters, an output schema present, and the cross-tool prerequisite stated, the definition is largely complete for a list-style tool. Minor omissions like pagination behavior or an explicit read-only statement are acceptable at this complexity level but prevent a 5.

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

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

Schema description coverage is 0%, so the description must compensate. It does: asset_type gets explicit enum values in prose, and bc_id gets provenance ('Use get_business_centers_tool first to get bc_id'). It stops short of describing bc_id's format or giving examples, but it makes both parameters meaningfully usable.

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?

Description states a specific verb and resource ('Get all assets of a given type within a Business Center') and explicitly enumerates the three valid asset types (ADVERTISER, PIXEL, CATALOG), which differentiates it from siblings like get_video_assets_tool and get_pixels_tool. The scope and return fields are 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?

Provides clear sequencing guidance: 'Use get_business_centers_tool first to get bc_id,' which tells the agent what must happen before invoking this tool. It does not explicitly state exclusions or direct the agent to alternatives for other asset types, so it earns a 4 rather than 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 provided, so the description carries the burden of behavioral disclosure. It does disclose the return fields and the prerequisite of bc_id, which is helpful. However, it does not mention whether this is a read-only operation, whether it requires special permissions, or whether it returns paginated results. For a read-only list tool, this is adequate 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?

Three sentences with no filler. The first sentence states the core function, the second lists return fields, and the third gives usage guidance. Every sentence earns its place and the most important information is front-loaded.

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

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

For a simple one-parameter read tool with an output schema, the description is nearly complete. It covers what the tool does, what it returns, and how to obtain the required parameter. The only minor gap is the lack of explicit read-only/permission context, but the output schema and simple parameter make this a minor omission.

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

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

Schema description coverage is 0%, so the description must compensate. It explains that bc_id is the Business Center identifier and instructs the agent to get it from get_business_centers_tool first. This adds meaning beyond the bare schema property 'Bc Id' and effectively documents the only parameter.

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

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

The description states a specific verb ('Get'), a specific resource ('all members of a Business Center'), and the exact data returned (user_id, username, email, role, status). It clearly distinguishes itself from sibling tools like get_business_centers_tool and get_bc_assets_tool by focusing on members and access status.

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

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

The description explicitly says to use get_business_centers_tool first to obtain bc_id, which is a clear prerequisite and usage instruction. It also states the tool is 'Useful for access audits,' giving a concrete use case. This is strong guidance for an agent deciding when to invoke 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 provided; description implies read-only access but lacks details on pagination, rate limits, or behavior when no centers are returned.

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

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

Single sentence is concise but too minimal, missing parameter details and usage context. It is front-loaded but under-specified.

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 presence of an output schema, the description partially covers return values, but it omits pagination behavior and filtering semantics, making it incomplete for a 3-parameter 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 coverage is 0% and description provides no explanation of page, bc_id, or page_size parameters, leaving the agent to infer their purpose.

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 retrieves business centers accessible by the current token. It distinguishes from sibling tools focused on ads and reports.

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

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

No guidance on when to use this tool vs alternatives, no exclusions or prerequisites 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?

No annotations are provided, so the description carries full burden. It only mentions retrieving campaigns with optional filtering, but does not disclose side effects (likely none), permissions, pagination, or rate limits. Minimal transparency for a data retrieval 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 sentence of 10 words, very concise. However, conciseness comes at the expense of missing crucial details. It earns a mid score because it is not verbose but could include more information without becoming long.

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

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

Given no annotations, 0% schema coverage, and an existing output schema (unseen), the description is incomplete. It does not explain return format, filtering syntax, or prerequisites needed for an agent to correctly invoke the 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?

With 0% schema description coverage, the description must compensate. It mentions 'optional filtering' which hints at the filters parameter, but provides no details on format or allowed keys. The advertiser_id is partially explained via 'specific advertiser', but overall adds little value beyond parameter names.

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 retrieves campaigns for a specific advertiser with optional filtering. This verb+resource+scope pattern is specific and distinguishes it from siblings like get_ad_groups_tool (different resource) or get_gmvmax_campaigns_tool (different scope).

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

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

No explicit guidance on when to use this tool versus alternatives such as get_ad_groups_tool or get_gmvmax_campaigns_tool. The description implies usage for advertiser campaigns but lacks when-not-to-use or alternative recommendations.

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 behavioral disclosure. It does state the output fields (fatigue_status, fatigue_level, recommendations) and notes optional filtering by ad_ids. However, it does not mention pagination behavior, data scope, auth requirements, or other operational traits, leaving a noticeable 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?

Two concise sentences front-load the core action, add a one-line definition, list the return fields, and note the optional filter. No filler or redundant restatement.

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 plus output schema covers the main purpose and return values, but for a tool with 4 parameters, no annotations, and no schema descriptions, it leaves out pagination semantics and any guidance on when not to use it. 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 0%, so the description must compensate. It only clarifies ad_ids as an optional filter; advertiser_id, page, and page_size are left unexplained beyond their names. That is insufficient compensation for 4 undocumented 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 opens with a specific verb plus resource: 'Get creative fatigue scores per ad.' It then defines what fatigue means ('shown too frequently... needs refreshing'), which differentiates it from sibling getters like get_reports and get_video_performance. No ambiguity about the tool's purpose.

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 gives clear context: use this when you need to determine whether ads have been shown too frequently to the same audience and need refreshing. It does not explicitly name alternatives or exclusion conditions, so it stops short of a 5, but the intended use is clear.

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 carry the full burden. It does disclose that the tool returns event sets and lists specific fields, but it never explicitly states it is read-only, nor does it mention any pagination, permissions, or side effects. The implied read-only nature covers some ground, but more explicit transparency would be better.

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 three sentences with no fluff. It leads with the primary action, then explains what is shown, then lists the return fields. Every sentence earns its place, 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?

The description covers the core purpose, the scope, and the return fields. Given that an output schema exists to detail the response structure, this is fairly complete. However, it omits any mention of pagination, error conditions, or the need for advertiser_id (though that is in the schema), so it's not fully exhaustive.

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

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

Schema coverage is 0%, so the description must compensate. It does give context by saying 'configured for an advertiser', tying the advertiser_id to the resource being listed. However, it doesn't explain the format, constraints, or why the parameter is required beyond that. This adds some meaning but not a thorough explanation.

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 ('List') and the resource ('offline conversion event sets') plus the scope ('configured for an advertiser'). It's specific enough, but does not explicitly distinguish it from sibling tools like get_pixels or get_campaigns, so it misses the top score for sibling 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 is given on when to use this tool versus alternatives. It doesn't mention prerequisites, fail conditions, or scenarios where another tool would be preferred. With a large sibling set, this omission hurts discoverability.

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 does disclose the output shape ('Returns one row per pixel per event type per day') and the prerequisite for pixel_ids. This gives the agent a good sense of what to expect and what is needed. It does not explicitly state that the operation is read-only or has no side effects, but the 'get' prefix and the nature of the tool imply a safe read operation. It also doesn't mention rate limits or error handling, but for a stats tool, the provided details are sufficient. The output format and prerequisite are valuable behavioral traits beyond the schema.

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 three sentences, each adding distinct value: purpose, usage prerequisite, and output/date format. It is front-loaded with the core purpose, and there is no fluff or redundancy. It is efficient and well-structured, earning a high score.

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 4 parameters, no annotations, and an output schema is indicated. The description covers the purpose, the output shape ('Returns one row per pixel per event type per day'), and the prerequisite for pixel_ids. It also specifies the date format. It does not mention potential limits (e.g., date range restrictions, pixel count limits) or error conditions, but given the output schema exists and the tool is relatively simple, the description provides enough context for an agent to call it correctly. The missing advertiser_id clarification is a minor 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?

Schema description coverage is 0%, so the description must compensate. It clarifies the date format: 'Dates are YYYY-MM-DD,' which directly explains start_date and end_date. It also explains the source of pixel_ids: 'Use after get_pixels_tool to get pixel_ids.' This adds meaning beyond the raw schema. It does not explicitly describe advertiser_id, but that is likely self-explanatory from its name. The description also ties pixel_ids to the output granularity ('per pixel'), which is helpful. Given the zero coverage, it does a good job of illuminating the key parameters, though it could have added a brief note on advertiser_id.

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 function: 'Get aggregated conversion event counts (Purchase, AddToCart, ViewContent, etc.) per pixel over a date range.' It specifies the resource (pixel event counts), the action (get), and the scope (per pixel, per date range). It also distinguishes itself from siblings by mentioning 'Use after get_pixels_tool to get pixel_ids,' indicating a specific workflow that separates it from other reporting tools. This is a specific verb+resource with clear 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?

The description provides a clear usage prerequisite: 'Use after get_pixels_tool to get pixel_ids.' This tells the agent that pixel_ids must be obtained from another tool first, which is a concrete when-to-use instruction. However, it does not explicitly compare with alternative reporting tools like get_reports_tool or the async report tools, nor does it state when not to use this tool. It gives clear context but lacks explicit exclusions or alternatives.

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 the return fields (pixel_id, pixel_name, pixel_code, etc.) and mentions that it shows whether measurement is set up correctly, which is useful. However, it does not describe pagination behavior, rate limits, or side effects. As a read-only getter, this is partially sufficient 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?

Two sentences with zero wasted words. The main action is front-loaded, and the return fields are listed compactly. Excellent structure for quick scanning.

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

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

The description covers the core purpose and return fields, but it lacks usage guidance and parameter semantics. Pagination via page/page_size is implied but not explained, and the output schema (though present) is not described. For a simple list tool it is adequate, but missing details prevent full self-sufficiency.

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

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

Schema description coverage is 0%, meaning the schema provides no parameter descriptions. The tool description does not compensate: it only implies advertiser_id by saying 'for an advertiser' but offers no explanation of page, page_size, or their defaults. This is a significant gap for a 3-parameter tool.

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 verb 'List' and resource 'TikTok Pixel installations' for an advertiser, and clarifies that it shows conversion events and measurement status. It is distinct from sibling get_pixel_event_stats_tool (which focuses on event statistics), though it does not explicitly name that alternative. 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?

No guidance on when to use this tool versus alternatives. It does not mention any related tools, exclusions, or conditions for use. An agent has no context on when this is preferable to other getters like get_pixel_event_stats_tool or get_reports_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 full burden. It implies a read operation but doesn't disclose side effects, permissions, rate limits, or return format beyond 'reports and analytics'.

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, which is concise, but it lacks necessary details. It is front-loaded but not efficiently structured to convey essential information.

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

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

Given 18 parameters, no annotations, and an output schema present but not described, the description is severely incomplete. It fails to provide sufficient context for an agent to correctly invoke the 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 0%, and the description only vaguely mentions 'filtering and grouping options' without explaining any of the 18 parameters (e.g., filters, dimensions, metrics).

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 gets performance reports and analytics with filtering and grouping, but it doesn't differentiate from sibling tools like get_ads_range_report_tool or get_gmvmax_reports_tool that may have similar purposes.

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

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

No guidance on when to use this tool versus alternatives, no exclusions, and no context about prerequisites or typical use cases.

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 explaining behavior. It openly states that Smart+ campaigns are excluded from get_campaigns_tool, lists returned fields, and gives status filter examples. It does not discuss pagination behavior or side effects, but the get semantics and return-field disclosure provide meaningful transparency.

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

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

The description is compact and front-loaded: purpose first, then the key differentiator from get_campaigns_tool, followed by returned fields and filter examples. Every sentence carries information and there is no filler.

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 provides enough to call the tool correctly for typical use, and an output schema exists to cover return details. It could be more complete by explaining pagination parameters and campaign_ids filtering, but those are reasonably inferable and not critical 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?

Schema description coverage is 0%, so the description must compensate. It adds useful meaning for 'status' with concrete filter examples ('ENABLE', 'DISABLE', 'DELETE') and implies advertiser_id's role)Skip. However, page, page_size, and campaign_ids are not explained, leaving the agent to infer their semantics from names alone.

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 retrieves Smart+ (AI-optimised) campaigns for an advertiser, with a specific verb and resource. It also explicitly distinguishes itself from get_campaigns_tool by noting that Smart+ campaigns do not appear there, eliminating ambiguity.

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 gives a direct usage cue: use this when Smart+ campaigns are relevant, since they are absent from get_campaigns_tool. It explicitly names the sibling alternative and explains the blind spot this tool fills, so an agent can route 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 provided, the description carries the full burden, and it delivers the key behavioral facts: it returns a list of interest categories, specifies the returned fields, and notes optional filtering by objective_type. It does not discuss pagination or error behavior, but for a simple read-style getter the disclosed behavior is sufficient.

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?

Four concise sentences flow logically: what it does, what it returns, how to use the output, and the optional filter. Every sentence adds useful information, and the purpose is front-loaded with no filler.

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 output schema covers return-value structure, so that gap is already filled. The description covers purpose, usage context, and the optional parameter. The main missing piece is a clearer explanation of advertiser_id's role in determining the available categories, but the overall definition is strong enough for an agent to invoke it correctly.

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

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

Schema description coverage is 0%, so the description must compensate. It does explain objective_type with example values ('TRAFFIC', 'CONVERSIONS') and optionality, but advertiser_id—a required parameter—receives no semantic explanation beyond the schema title 'Advertiser Id.' This is partial compensation only.

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 opens with a specific verb and resource: 'Get all available interest categories for audience targeting.' It also lists the returned fields (IDs, names, levels, sub-category IDs), making the tool's purpose unmistakable and distinct from siblings like get_audience_reach_tool, which is about audience size rather than interest taxonomy.

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 gives clear operational context: 'Use the returned interest_category_id values when setting up ad group targeting' and explains the optional objective_type filter. It does not explicitly mention alternatives or when not to use this tool, but the intended use case is clear enough.

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 communicates that this is a read-oriented browsing operation and discloses the returned fields and filtering capability. However, it does not mention pagination behavior, response limits, or any operational side effects.

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

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

The description is compact and front-loaded with the core purpose, followed by useful return-field information and filtering guidance. Every sentence adds value and there is no redundancy.

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

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

The description covers the main purpose, return fields, and a filtering example, and an output schema exists. However, it omits pagination semantics and any guidance on when to use this tool versus related video or asset tools, leaving moderate gaps for an agent planning a call.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaningful semantics for the filtering object by mentioning the 'video_name' key and implies advertiser_id via 'for an advertiser'. However, it does not explain the page or page_size parameters, leaving part of the parameter space undocumented.

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 with a specific verb ('Browse') and resource ('creative video asset library for an advertiser'). It also lists the exact return fields, distinguishing it from sibling tools like get_campaigns_tool or get_video_performance_tool.

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 choose this tool over alternatives or when not to use it. The description implies use when browsing video assets, but it does not explicitly mention sibling tools or exclusion 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?

With no annotations provided, the description carries the behavioral disclosure burden. It discloses metric scope, required filter conditions, data_level choices, and date format, which helps. However, it does not mention pagination behavior, date-range limits, or other API-level caveats such as auth or rate limits.

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

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

The description is compact and front-loaded, with the purpose stated first, metric list in a clear block, and constraints in short, direct sentences. Every sentence adds useful information with no filler.

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 10-parameter tool with output schema presentheb, the description covers the core invocation requirements: purpose, required ID filter, valid data_level values, and date format. It lacks detail on dimensions and pagination, but an agent can reasonably invoke the tool with the information provided.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaning for data_level, date format, and the conditional requirement on campaign/adgroup/ad IDs. However, several parameters such as dimensions, page, and page_size are left unexplained, and the description does not cover all 10 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 states a specific verb and resource: 'Get TikTok-specific video engagement metrics' and enumerates the exact metrics returned. It explicitly positions the tool against the 'standard integrated report', distinguishing it from sibling reporting 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 clearly notes that at least one of campaign_ids, adgroup_ids, or ad_ids is required)Skip and specifies valid data_level values and date format. It gives a clear usage context via 'not available in the standard integrated report', though it does not explicitly name sibling alternatives or provide when-not-to-use guidance.

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