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

With no annotations provided, the description carries full burden. It discloses key behaviors: executing exactly one recommendation, safety guardrails (blast-radius caps, rate limits, auto-rollback), and non-interference with other pending recommendations. This is strong for a mutation tool, though it does not mention return values or error handling.

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, directly stating the action and then the safety constraints. No filler or repetition; every clause adds meaningful information. It is well-structured for quick parsing.

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 (2 required string params, no output schema, no nested objects), the description covers purpose, scope, safety features, and effect on other recommendations. It could mention the return value, but overall it is sufficiently complete for an agent to invoke 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 coverage is 100% with both parameters described as 'from list_recommendations', making the parameters self-explanatory. The description adds minimal semantic value beyond 'ONE' and 'already-diagnosed', which slightly reinforces the schema but does not compensate for any gaps. 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 uses specific verb 'Approve and execute' and specifies the resource as 'ONE already-diagnosed optimization recommendation', clearly distinguishing it from sibling tools like list_recommendations or check_approval. It conveys the exact action and scope without 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 establishes clear usage context: it is for approving and executing an already-diagnosed recommendation, with safety guardrails. It also clarifies that other pending recommendations remain untouched, which hints at when this tool is appropriate. It does not explicitly name alternatives, but the context strongly implies its niche.

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 excels by explaining the action implications: approval cannot be completed via API, the campaign is live and spending immediately upon execution, and the user can pause from the dashboard. It also lists all statuses, giving a complete picture of possible outcomes.

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

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

The description is extremely concise, consisting of two sentences that front-load the purpose in the first sentence and provide actionable guidance in the second. It avoids repetition, fluff, and overly technical jargon, earning its words.

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

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

For a simple tool with one parameter, no output schema, and no annotations, the description is remarkably complete. It explains the tool's purpose, enumerates all possible statuses, and gives user-facing instructions for the two critical states (pending and executed). The only omission is the exact return format, but the description effectively conveys that the status is the key output, making it sufficient for an AI agent to invoke and interpret 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?

The input schema already fully describes the single parameter approvalId as 'The approvalId returned by request_publish,' providing 100% schema coverage. The description reiterates this connection but adds no additional semantic detail beyond the schema, 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 function: 'Check the status of a publish approval created with request_publish.' It uses a specific verb ('check') and resource ('publish approval'), differentiates from siblings by referencing the companion tool request_publish, and enumerates the exact status values, 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 provides clear context for when to use this tool (after request_publish) and what to do with the result (remind user to open the approval link while pending, notify them the campaign is live and spending once executed). It also states a limitation ('approval cannot happen through the API'), giving a when-not perspective. However, it does not explicitly name alternative tools or explicitly say 'use this when X, not Y,' which prevents a perfect score.

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 fully carries the burden of behavioral disclosure. It mentions the 13-credit cost, the asynchronous nature (server-side, returns jobId), that nothing is published, no ad money is spent, and that the draft must be applied manually. This is thorough and transparent for a preview 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 front-loaded with the primary purpose and returns, then covers cost, jobId polling, and the crucial limitation about publishability. Every sentence serves a distinct informative function, and the warning is important to prevent misuse. It is appropriately sized for the tool's complexity.

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 no output schema, the description explains the return value ('Returns a jobId') and the necessary next step ('poll get_strategy_status'). It also covers cost, side effects (none), and how to eventually create a real campaign. Given the tool's async nature and credit cost, the description is 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 descriptions already provide high coverage (100%) of all four parameters, so the baseline is 3. The tool description does not add much beyond what's in the schema; it reiterates category, budget, and locations but doesn't provide additional parameter semantics such as types, constraints, or relationships beyond the schema.

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

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

The description clearly states the tool's function: 'Preview a DRAFT campaign strategy server-side' with specifics (keywords, ad copy, 3+ ad groups) and explicitly distinguishes it from publish-related siblings by noting it does NOT create a publishable campaign. The verb 'Preview' plus resource 'campaign strategy' and output 'jobId' make 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 provides explicit usage guidance: it names the follow-up tool 'get_strategy_status' to poll with the returned jobId, and explicitly states that 'request_publish cannot act on it', telling the user to apply the draft via a URL instead. This clearly delineates when to use this tool versus 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?

With no annotations, the description carries the full burden. It discloses the computation method ('rolling up the latest diagnostics'), the output format (letter grade and breakdown), and the optional scoping. It doesn't mention permissions or side effects, but given the read-only nature of computing a health score, the disclosure is adequate and adds meaningful 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 two sentences, front-loaded with the primary purpose, and avoids extraneous details. Each sentence adds value: the first explains what the score is and how it's computed, the second describes the return values and optional scoping.

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?

No output schema exists, so the description appropriately explains the return values (letter grade and per-dimension breakdown). It covers the essential behavior and edge cases (account-level vs campaign-level scope). It doesn't explain edge cases like no campaigns or grade thresholds, but these are not critical for using 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 100%, with the campaign_id parameter fully documented in the schema itself. The description only repeats 'Optionally scope to a single campaign', adding no new semantic meaning beyond what the schema already provides. 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 function: 'Compute a 0-100 account health score across 6 dimensions' and details the output ('Returns a letter grade A-F and per-dimension breakdown'). This distinguishes it from sibling tools like get_diagnostics, which likely provides raw diagnostics rather than an aggregated health score.

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 clear context by explaining that it rolls up diagnostics from all campaigns and optionally scopes to a single campaign. It implies when to use this tool (when an overall health score is needed) versus pulling raw diagnostics, but does not explicitly mention alternatives or exclusions.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states that performance metrics cover the last 7 days and that active diagnostics are included. This reveals the time window and scope of results. It does not mention response format or error handling, but for a read-only get operation, it is sufficiently 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 a single sentence, efficiently enumerating all included elements in a compact, readable format. It is front-loaded with the core purpose and avoids unnecessary words.

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

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

For a tool with one parameter and no output schema, the description provides a thorough list of what will be returned, including specific metrics and diagnostics. It is complete for its complexity, giving the agent a full picture of the tool's output without needing an output schema.

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% description coverage for the single parameter (campaign_id), including details about full UUID vs. short prefix. The tool description itself adds no additional parameter information. Per the rubric, baseline 3 applies when schema coverage is high.

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: retrieving a detailed view of a single VibeAds campaign. It lists the specific data returned (budget, bidding strategy, ad groups, locations, landing pages, performance metrics, diagnostics), making it unmistakably distinct from siblings like list_campaigns.

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

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

The description implies usage: you'd use this when you need comprehensive details for one campaign. However, it does not explicitly mention alternatives or when not to use it, such as 'for a list of campaigns, use list_campaigns' or 'for diagnostics only, use get_diagnostics'. The guidance 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 full burden. It discloses the return fields (severity, affected metric, current value vs benchmark, recommended action) and filtering options, but it claims a 'full list' while the schema indicates a default limit of 20, which is a minor inaccuracy that could mislead an agent. It also doesn't mention response shape or pagination.

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-structured sentence that front-loads the main purpose and includes relevant return details. Every word earns its place, though 'full' overstates the limit behavior.

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 no output schema, the description provides useful return fields and filter options, but it lacks explicit response shape and pagination behavior. The 'full list' misstatement and absence of limit handling details leave gaps given the tool's complexity.

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

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

The input schema covers 100% of parameters with descriptions, including defaults for limit and severity and the optional campaign_id. The description adds no substantive parameter semantics beyond the schema; it merely restates severity filtering and campaign scoping, so the baseline score 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 uses the specific verb 'Return' and identifies the resource as 'diagnostics' with scope 'across all campaigns', clearly distinguishing it from siblings like get_account_health_score and get_campaign_details. It also lists the return fields, which solidifies 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 clearly states that the tool returns all active diagnostics and can be filtered by severity and campaign, giving a strong sense of when to use it. However, it does not explicitly mention when not to use it or name alternatives, so the agent must infer from the diagnostics focus that other sibling tools are for different purposes.

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 disclosing behavior. It clearly states that the tool returns a ranked list of terms to negate and positive terms, and that it can be scoped to a campaign. The 'Analyze' verb implies a read-only operation, and no side effects are mentioned. It does not detail permissions or rate limits, but for an analysis tool, the output and scoping are well 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 two sentences, front-loaded with the core action and purpose, then summarizing the output and scoping. No word is wasted, and it avoids repetition of schema details. It is concise and well-structured.

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 moderate-complexity tool with a complete schema and no output schema, the description sufficiently explains what the tool does and returns. It covers the key use cases (wasted spend and winning terms) and the optional campaign scoping. It does not elaborate on ranking algorithm or thresholds, but that is not necessary for an agent to select and 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 100% for the three parameters, so the baseline is 3. The description adds value by connecting the parameters to their purpose: 'high-cost terms with zero conversions' clarifies min_cost, 'last N days' aligns with lookback_days, and 'scoped to a single campaign' directly explains campaign_id. This extra context enriches the schema-only definitions.

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 ('Analyze') with a clear resource ('search terms') and explicitly states the twofold purpose: finding wasted spend (high-cost terms with zero conversions) and winning terms (high conversion rate). It distinguishes itself from sibling tools like list_campaigns and get_campaign_details by focusing on search term analysis rather than campaign listing or 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 provides clear context for when to use the tool: to analyze search terms for optimization opportunities. It mentions optional scoping to a single campaign, which is a usage nuance. However, it does not explicitly name any alternative tools or state when not to use it, so it stops short of full exclusion guidance.

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

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

No annotations exist, so the description carries the full burden. It discloses the two phases (running vs complete), what is returned in each phase, and the crucial fact that the draft is only a preview and not publishable via request_publish. This is rich behavioral context beyond a simple 'get status' statement.

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, front-loaded with purpose, then usage timing, then an important caveat. Every sentence earns its place with 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?

For a single-parameter polling tool without an output schema, the description adequately covers what the tool does, when to use it, what it returns, and a critical limitation. No important context 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 jobId as 'The jobId returned by generate_strategy' with 100% coverage. The description adds no new parameter-specific information; it only reinforces the same provenance. Baseline 3 is appropriate when schema does 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 clearly states the tool polls the status of a strategy generation job started with generate_strategy, and specifies what it returns (status and phase while running, drafted ad groups once complete). It distinguishes itself from siblings like generate_strategy (which starts the job) and request_publish (which cannot publish previews).

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?

Explicit usage guidance is provided: poll every 10-15 seconds until status is completed or failed. It also tells the agent what to do with the result (show the preview and point to the app URL) and explicitly warns that request_publish cannot publish a preview, effectively naming an alternative to avoid.

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 discloses the scope (managed by VibeAds, for the authenticated user) and the return fields (name, status, category, budget, high-level metadata). However, it does not explicitly state that this is a read-only operation with no side effects, nor does it mention pagination or that the 'all' default is constrained by the limit parameter. This is adequate but leaves some behavioral ambiguity.

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. The first sentence states the action and resource. The second provides return fields and usage guidance. Every word contributes value, and the critical 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 list tool with two well-documented parameters and no output schema, the description covers the essentials: what it lists, for whom, and what data is returned. The only notable gap is the lack of explicit mention that the result may be paginated/limited, which could mislead an agent expecting truly 'all' campaigns. Otherwise, it is complete enough 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?

Schema description coverage is 100%: both limit and status have descriptive text and defaults. The description adds no extra parameter-level detail, such as how limit interacts with 'List all' or how status filtering works. Since the schema already documents the parameters, a 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 uses a specific verb ('List') and clearly identifies the resource ('Google Ads campaigns managed by VibeAds for the authenticated user'). It also differentiates from siblings by positioning itself as the discovery tool ('Use this first to discover which campaigns exist before drilling in'), which contrasts with get_campaign_details for deeper inspection.

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 tells the agent when to use it ('Use this first') and that it precedes drilling into details. It does not name alternatives or state when not to use it, but the sibling tool names make the sequencing clear. This is strong contextual guidance, though not a full when/when-not breakdown.

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 discloses the tool lists pending items, groups them by optimization session, includes detailed fields (action, reason, risk level, etc.), and supports optional campaign scoping. The term 'List' implies a read-only operation, which is the key behavioral trait. It doesn't mention pagination or empty-result behavior, but essential behavior is covered.

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: the first states the main purpose and grouping; the second details return contents and optional scoping. It is front-loaded, concise, and every sentence adds value with 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 tool is simple with one optional parameter and no output schema. The description compensates well by listing return fields, grouping behavior, optional scope, and the connection to approve_recommendation. Minor omissions like pagination and sorting are not critical for this tool's complexity.

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

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

Schema coverage is 100% for the single optional campaignId parameter, and its description already explains scope. The tool description repeats 'Optionally scope to one campaign' but adds no new semantic meaning beyond the schema. Baseline 3 is appropriate.

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

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

The description uses the specific verb 'List' and clearly defines the resource: pending optimization recommendations awaiting approval. It also distinguishes itself from sibling tools like approve_recommendation by noting it returns the sessionId and recommendationId needed for that action, making its role 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?

The description implies when to use this tool: when you need pending recommendations awaiting approval, and it explicitly mentions the IDs needed for approve_recommendation, signaling a clear workflow. It also notes optional campaign scoping, though it doesn't explicitly list alternatives or exclude other 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 provided, but the description fully carries the burden: it discloses that publishing spends real money, that a human-approval URL is returned, that the API key cannot approve, and that the campaign goes live immediately after approval.

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?

Though detailed, every sentence adds essential information about the approval flow. It is well-structured and front-loaded with the core action, then explains the human-approval process and follow-up polling.

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 no output schema and no annotations, but the description explains the return values (approvalUrl, approvalId) and the full flow with check_approval. It is complete for a complex publish action with human approval.

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 100% of parameters, and the description adds meaningful context beyond the schema: the campaignId must be an existing campaign with ad groups, and it references list_campaigns as the source. This is more than a 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?

Clearly states the verb 'Start the publish flow' and the resource 'EXISTING campaign', and distinguishes from generate_strategy previews. It also explains the outcome (returns approval URL, campaign goes live on approval).

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

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

Explicitly says when to use: for existing campaigns found via list_campaigns, and explicitly excludes generate_strategy previews. It also directs the follow-up action to poll check_approval with the approvalId.

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