OrbiAds
OfficialServer Quality Checklist
Latest release: v0.1.2
- Disambiguation4/5
Most tools have distinct purposes with detailed descriptions that help differentiate them. However, some tools like audit, audit_skill, and gam_audit could be confused, as they all relate to auditing but with subtle differences. The names alone don't always clarify the distinction.
Naming Consistency3/5Tool names are inconsistent: some are single nouns like 'audit' and 'billing', others are verb_noun like 'check_credentials' and 'initiate_gam_auth'. There is no uniform pattern, though most names are descriptive. The mix of conventions reduces predictability.
Tool Count3/5With 47 tools, the server is extensive. While each tool has a specific purpose in GAM management, the high number may be overwhelming. Some tools could potentially be merged (e.g., line_items and line_item_lifecycle), but the scope justifies many specialized operations.
Completeness5/5The tools cover a comprehensive range of GAM operations including authentication, inventory, orders, line items, creatives, deals, reporting, auditing, admin, and specialized areas like prebid, DAI, and yield. The surface appears complete for a full campaign lifecycle.
Average 4.5/5 across 47 of 47 tools scored. Lowest: 3.2/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 126 commits in the last 12 weeks
- Last stable release on
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
This repository includes a glama.json configuration file.
If you are the author, simply .
If the server belongs to an organization, first add
glama.jsonto the root of your repository:{ "$schema": "https://glama.ai/mcp/schemas/server.json", "maintainers": [ "your-github-username" ] }Then . Browse examples.
How to sync the server with GitHub?
Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.
To manually sync the server, click the "Sync Server" button in the MCP server admin interface.
How is the quality score calculated?
The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).
Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.
Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).
Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.
Tool Scores
- Behavior3/5
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 states MODE: mixed (read + write), AUTH: OAuth 2.0 required, and CREDITS: read = 0 credits, which implies some write operations may consume credits. However, it does not describe potential destructive actions, error behavior, rate limits, or the exact credit cost for writes. The OUTPUT is vague. This is acceptable but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the purpose but contains redundancy: 'Ad Rules, Content metadata, and Content bundles' appears both in the header and the 'WHEN TO USE' section. The metadata lines are useful but could be integrated more tightly. Overall, it is adequate but not maximally concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 10 sub-operations and the schema allows additional properties (additionalProperties: true), but the description does not explain what extra parameters are required for each action. This is a significant gap for an agent to correctly invoke the tool. Output schema is absent, but the primary issue is the missing sub-parameter documentation. The description is incomplete for a multifunction tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the two defined parameters. The action enum has detailed descriptions for each value, and network_code has a clear description. The description adds minimal extra meaning beyond the schema, such as the vague 'OUTPUT: Results for video ops entities.' With high coverage, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5Does the description clearly state what the tool does and how it differs from similar tools?
The description states it is for video monetization and lists three areas: ad rule management, content metadata, and content bundle operations. The tool name 'video_ops' is generic, but the description clarifies the scope. Sibling tools like 'creatives' or 'line_items' do not directly overlap, so the purpose is fairly clear, though it could be more specific about what each area entails.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a 'WHEN TO USE' section: 'Use for managing Ad Rules, Content metadata, and Content bundles.' This provides clear context but does not specify when not to use the tool or suggest alternatives. No exclusions are mentioned, and sibling tools are not referenced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Only discloses that it is public, but no details on safety, side effects, or data characteristics. Insufficient for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with no wasted words. Efficient and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no parameters or output schema, the description is minimal. It does not explain what 'public health and catalogue summary' returns, leaving the agent under-informed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so the description does not need to add param info. Baseline 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'public health and catalogue summary', which indicates a summary function but is vague. It differentiates from sibling tools by implying this is for public info, but lacks a specific verb+resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The hint 'Real Google Ad Manager operations require OAuth' suggests this tool is for public data without OAuth, providing clear usage context. No explicit exclusions, but helpful guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description bears full responsibility for behavioral disclosure. It states MODE (mixed), AUTH, and CREDITS, but lacks details on side effects of write operations (e.g., irreversibility, permission requirements). Score 3 reflects moderate transparency with gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is structured with clear sections and is relatively concise. However, the first sentence and the 'WHEN TO USE' section are somewhat redundant, preventing a top score. Score 4.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of 5 sub-actions and the absence of an output schema, the description provides an overview but lacks details on return values, error handling, or prerequisites beyond OAuth. Additional context would be needed for full completeness. Score 3.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with both parameters well-described in the schema. The tool description adds general context (MODE, OUTPUT) but does not enhance parameter-specific meaning, leading to a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the domain (yield optimization group management and forecast governance) and lists specific sub-operations. However, it does not provide a single focused verb+resource and lacks explicit differentiation from sibling tools, resulting in a score of 4.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes dedicated sections for MODE, AUTH, CREDITS, OUTPUT, and WHEN TO USE, offering clear context for usage. However, it does not specify when not to use this tool or mention alternatives, justifying a score of 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that operations are mixed (read/write), requires OAuth 2.0, and notes credit costs for read vs write. It describes what each action does but lacks details on side effects, idempotency, rate limits, 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.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, using short sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE). Every sentence adds value; no filler. Front-loaded with core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 2 parameters and no output schema, the description covers key aspects: purpose, sub-actions, auth, credit costs, and output type. It lacks details on pagination, error handling, and search filters, but is fairly complete given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with detailed enum descriptions for 'action' and clear type for 'network_code'. The description adds overall context but does not enhance parameter meaning beyond the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it is for searching and moderating Ad Exchange creatives in GAM Ad Review Center. The verb-resource pair is specific ('search and moderate' + 'Ad Exchange creatives'), and the context ('GAM Ad Review Center') clearly distinguishes it from sibling tools like 'creatives' which handle different ad operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a 'WHEN TO USE' section that specifies the scenario: finding, allowing, or blocking marketplace creatives before they serve. It also notes the mode (mixed), auth requirement, and credit costs. However, it does not explicitly state when not to use this tool or mention alternative tools for other ad operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It covers side effects (user deactivation/removal affects access control, label changes propagate), auth needs, credit costs (reads=0, writes=0.5), and output types per sub-area. Does not mention rate limits or error conditions, but given complexity, it's thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with headings (MODE, AUTH, CREDITS, OUTPUT, SIDE EFFECTS, WHEN TO USE). Front-loaded with summary. Could be slightly more concise, but organization aids readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers many aspects (side effects, auth, credits, when to use). However, fails to mention that sub-operations may require additional parameters beyond action and network_code (schema has additionalProperties: true). Also lacks return value format details. Adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed enum descriptions for action and network_code. The description adds overall context (auth, credits) but does not significantly enhance individual parameter 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.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it's a GAM admin orchestration tool with 48 operations across 7 administrative areas. It provides a specific verb+resource summary and distinguishes from sibling 'targeting' tool in the WHEN TO USE section.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
WHEN TO USE section explicitly recommends using gam_admin for network configuration and governance tasks, and suggests targeting for custom targeting key-values. Auth requirements (OAuth 2.0, Network Admin role for writes) are stated. Lacks explicit exclusion of other sibling tools but provides clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description fully covers behavioral aspects: MODE (mixed read/write), AUTH (OAuth 2.0), CREDITS (0 for reads, 0.5 for writes), SIDE EFFECTS (global impact, risk of breaking ad serving), and a caution to test in staging. This exceeds typical disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with labeled sections (MODE, AUTH, etc.) and a usage recommendation. It front-loads the purpose. However, some phrases (e.g., 'CreativeWrapper' repetition) could be tightened without loss of clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers return values (though no output schema), side effects, authentication, and credits. It is comprehensive given the tool's complexity. Minor gaps: lacks pagination details for list operations and error handling, but overall sufficient for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema descriptions for both parameters (action and network_code) are already detailed. The main description does not add extra meaning beyond what the schema provides, so it meets the baseline without improvement.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages CreativeWrapper entities and explains they inject scripts around creatives. It distinguishes from siblings by specifying its GAM entity focus. However, the verb 'manage' is somewhat generic, though the sub-actions in the schema narrow it down.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a 'WHEN TO USE' section specifying appropriate scenarios (e.g., injecting measurement scripts) and advises testing in staging due to side effects. It implicitly suggests using presets for templates, but does not explicitly contrast with sibling tools like creatives or inventory.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description discloses read-only mode, OAuth requirements, zero credits, and output type. This provides good behavioral context 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.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with clear sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE) and no redundant sentences. Front-loaded with purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers read-only nature and output, but lacks details on the additional properties (month/year) implied by the schema's additionalProperties:true. Missing details on parameter formats reduce completeness for a tool with unlisted required inputs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% coverage for defined parameters (action, network_code), but the description mentions month and year as implicit parameters not in the schema, adding context. However, it does not detail their formats or where to specify them, so value added is moderate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads MCM earnings for parent publishers, using specific verb and resource. It distinguishes from siblings as the only tool focused on Multi-Customer Management earnings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear when-to-use statement for publisher revenue reporting. However, it does not explicitly exclude alternatives or mention when not to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden for behavioral transparency. It discloses authentication (OAuth 2.0 required), credit costs (reads=0, writes=0.5 credits), and a key side effect (archive_advertiser deactivates the company). It also describes the output format. This covers critical behavioral traits, though side effects for other actions are not detailed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured, with clear sections (MODE, AUTH, CREDITS, OUTPUT, SIDE EFFECTS, WHEN TO USE). Every sentence adds value, and there is no redundancy. 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.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (12 sub-actions, 3 parameters, no output schema), the description provides key context: output summary, side effects, authentication, and credits. The action schema descriptions cover sub-action details. The description is largely complete, though more explicit error handling or per-action specifics could be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters and their descriptions thoroughly (including enum options for 'action'). The description adds no new parameter-level information beyond what's in the schema, so 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.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Manage GAM companies — advertisers, agencies, and contacts.' It provides a specific verb ('Manage') and resource ('GAM companies'), and sets context by noting that companies are required before creating orders, distinguishing it from order-related sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a 'WHEN TO USE' section that explains the tool is for managing advertiser/agency entities before creating orders. It gives clear context but does not explicitly state when not to use the tool or provide alternative tools. The guidance is clear and helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full load. It discloses MODE (mixed read+write), AUTH (OAuth 2.0 required), CREDITS (read = 0 credits), and OUTPUT (Results for DAI entities). This gives agents essential behavioral info, though it could mention that some actions (e.g., delete) are destructive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise and structured with clear MODE, AUTH, CREDITS, OUTPUT, and WHEN TO USE sections. Every sentence provides value with no redundancy. It is front-loaded with the key purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (14 actions) and the absence of an output schema, the description covers purpose, behavior, auth, credits, and output type. However, it does not mention that additionalProperties: true allows dynamic parameters for specific actions, which could be important for agents to know.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (both parameters have descriptions in the schema). The description itself adds no further parameter details beyond what is already in the schema. Baseline 3 is appropriate as the schema already handles parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'DAI (Dynamic Ad Insertion) and broadcasting operations' and specifies 'managing Dynamic Ad Insertion auth keys and encoding profiles'. The enum values in the action parameter further detail the specific operations. This distinguishes it from sibling tools like line_items or orders, which handle different GAM domains.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'WHEN TO USE' section explicitly says 'Use for managing Dynamic Ad Insertion auth keys and encoding profiles', providing clear context. However, it does not specify when not to use it or mention alternative tools for non-DAI operations, which would be helpful given the large set of sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses read-only mode, OAuth requirement, zero credits, and output format. Explains caching behavior (cached vs live-probe). No contradicting annotations. Lacks mention of rate limits or error handling, but adequate given annotations absence.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise with clear section headers (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE). Every sentence serves a purpose, no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, usage, auth, output, and actions well. Explains caching behavior and sub-action selection. Lacks details on default network_code behavior and error cases, but sufficient for a simple read-only tool with full schema coverage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds minimal semantic value beyond what is already in the schema's parameter descriptions, merely rephrasing the action enum values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Inspect GAM network features' with specific verb and resource, and the first line explicitly defines the tool's purpose. It distinguishes from siblings like 'gam_admin' and 'gam_jobs' by focusing on feature inspection.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance: 'Call before using advanced GAM features' and 'Use probe_gam_features when you need to test a specific capability live.' Includes context for when to use each sub-action, though does not exhaustively list all alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It explicitly states MODE (mixed read+write), AUTH (OAuth 2.0 required), CREDITS (list/get free, create/patch/delete are write operations), and OUTPUT (returns live stream ad break objects scoped by event/asset key). This disclosure is thorough, though it does not detail potential side effects or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at three sentences plus a structured block (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE). Every element serves a purpose, and it is front-loaded with the core function. No redundant or extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's mixed mode and multiple actions, the description covers all essential facets: purpose, auth, credits, output format, and usage guidance. The only gap is the lack of a detailed output schema, but the description compensates by stating the return type. The network_code source is noted. Complete for typical agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already has 100% description coverage for its two parameters (action with enum descriptions, network_code with source guidance). The description adds context about scoping by event/asset key but does not significantly enhance understanding 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.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Manage live stream ad breaks for GAM video workflows', which is a specific verb+resource. It further breaks down into five sub-operations (list, get, create, patch, delete) via the action parameter, distinguishing it from sibling tools focused on other aspects of ad management.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a dedicated 'WHEN TO USE' section: 'Use live_stream to inspect, create, update, or delete ad breaks for live video events.' It also specifies the MODE (mixed), AUTH requirements, and CREDITS cost, providing context for appropriate use. However, it does not explicitly mention when not to use or list alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description provides mode (mixed read+write), auth requirements (OAuth), credit costs per operation, side effects (state transitions, buyer notifications, irreversibility of termination). It lacks rate limit info but covers key behavioral traits well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with labels (MODE, AUTH, CREDITS, etc.) and bullet-style action list. It is fairly long but most sentences add unique value. Could be more concise, but organization aids readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with 2 parameters and no output schema, the description covers output types, side effects, and credit costs. It lacks explicit mention of error handling or pagination but is otherwise complete for agent decision-making.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds overall context like side effects and usage but does not provide additional detail on parameters beyond what the schema already includes. For high coverage, description adds marginal value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool authors and manages programmatic deals (PMP, PG/PD, ADCP, auction packages). It distinguishes from siblings by specifying to use the campaign tool for standard direct-sold campaigns. The summary verb 'Author and manage' plus the list of deal types provides precise scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (programmatic direct, PMP, ADCP) and when not to (direct-sold campaigns, pointing to campaign tool). Also provides credit costs and side effects like negotiation workflows, giving clear context for agent decisions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers behavioral traits: mixed read/write mode, OAuth 2.0 requirement, credit costs (free reads, possible charges for mutations), and output types. It also implies mutation for cleanup/update actions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured with labeled sections (MODE, AUTH, etc.) and front-loaded with overall purpose. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's multiple sub-actions, the description covers high-level outputs and credit costs. The action enum in schema provides specifics. However, no output schema exists, and per-sub-action return details could be clearer, but overall it's sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with detailed descriptions for action (enum with sub-action details) and network_code. The main description adds no extra parameter meaning beyond the schema, meeting the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Plan and operate Prebid.js / header bidding setup for GAM.' It lists specific actions (generate targeting keys, line items, preview, inspect, cleanup), making it distinct from sibling tools like creative_qa or dai_skill.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'WHEN TO USE' section provides explicit use cases, such as generating Prebid targeting keys or cleaning up artifacts. While it does not explicitly state when not to use or mention alternatives, the guidance is clear and contextual.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Although annotations are absent, the description discloses MODE (mixed read/write), AUTH (OAuth required), and CREDITS (0 credits). However, it does not explicitly state the destructiveness of delete operations in the main description; these details appear only in the input schema parameter descriptions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear labeled sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE). It is front-loaded with purpose and every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has multiple sub-actions and no output schema, the description covers usage context, output format, and sibling differentiation. However, it lacks details on error handling or edge cases (e.g., deleting a non-existent preset).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with detailed enum descriptions for 'action' and a clear description for 'network_code'. The main description adds little beyond summarizing the action categories, so it meets the baseline but does not add significant extra meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages OrbiAds tenant settings, naming conventions, delivery defaults, and configuration presets. It differentiates from sibling 'network' by specifying that network-level GAM settings should use that tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a 'WHEN TO USE' section that explicitly tells users to use this tool for tenant-level defaults and to use the 'network' tool for network-level GAM settings. It also provides AUTH and CREDITS context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It discloses read-only mode, OAuth requirement, zero cost, and output format with fields. However, pagination is only mentioned in the input schema's action description, not in the main description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with sections for mode, auth, credits, output, and usage guidance. Some redundancy in the 'NOT' comparisons, but overall efficient and front-loaded with purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers essential aspects: purpose, when to use, authentication, cost, output fields, and distinctions from similar tools. Lacks explicit pagination behavior and rate limits, but schema hints at pagination.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. Description adds value by listing filterable fields (entityId, entityType, userId, date range) that are only partially described in the schema's action parameter description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states tool queries GAM audit log for change history, with explicit verb 'Query' and resource 'GAM audit log'. Differentiates from siblings audit_skill and gam_audit with specific contrasts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit when-to-use: 'when you need to trace who changed what and when on a specific GAM entity'. Also specifies what it is not, naming alternative tools (audit_skill, gam_audit) and their purposes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses MODE (write, though one read-only sub-action exists), AUTH (OAuth 2.0), CREDITS (0.5 per action), OUTPUT (CreativeAsset objects with fields), and SIDE EFFECTS (storage quota, in-place compression). It does not cover rate limits or error handling, but overall is transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections and detailed action lists. While somewhat lengthy, the complexity of 15 sub-actions justifies the length. It is front-loaded with the main purpose and structured for easy scanning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description compensates by specifying return fields (assetId, fileName, etc.). It also covers auth, credits, and side effects. For a tool with many sub-actions and no output schema, it is reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by detailing each action sub-operation with syntax and behavior beyond the schema's enum definition. The network_code parameter also has a clear description. This exceeds the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Upload and create GAM creative asset files — images, HTML5, video, audio, and companion ads.' It also differentiates from sibling tools (creative_assets vs. creatives vs. creative_qa) in the WHEN TO USE section.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly provides WHEN TO USE guidance, distinguishing between creative_assets for file management, creatives for creative entity management, and creative_qa for validation. It also includes MODE, AUTH, CREDITS, OUTPUT, and SIDE EFFECTS sections, offering comprehensive context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses MODE (read+limited write), AUTH (OAuth 2.0 required), CREDITS (0/free), and OUTPUT format (Job objects with specific fields). While it doesn't detail side effects of duplicate_job, it adequately covers the behavioral profile 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.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Concise and well-structured: brief opening sentence, then sections for mode, auth, credits, output, usage. Front-loaded with primary purpose. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters (1 required) and no output schema, the description provides sufficient context: purpose, usage relative to siblings, behavioral traits, and parameter enumeration. Complete for its complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed parameter descriptions. The description reinforces the action parameter by mentioning sub-operations but does not add significant new meaning beyond what the schema already provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages OrbiAds campaign deployment jobs, distinct from GAM background jobs. It specifies the resource (jobs) and operation (manage, with sub-operations get, list, duplicate). This distinguishes it from siblings like gam_jobs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use this tool (check OrbiAds job status) and when to use the sibling gam_jobs (GAM backend operations). Also explicitly says 'NOT the same as gam_jobs', providing clear guidance on alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It conveys that the tool is mixed read+write, requires OAuth 2.0, consumes credits (reads = 0, writes = 0.5), and lists output fields. However, it could be more explicit about destructive operations beyond 'archive' and the consequences of batch operations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (summary, mode, auth, credits, output, when to use). It is concise, using bullet points and short paragraphs, with every sentence adding value. No redundancy or unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having 4 parameters and no output schema, the description provides comprehensive context: authentication, credit costs, output field list, explicit usage guidance against siblings, and a detailed action enum summary. This fully compensates for the missing output schema and ensures the agent can correctly invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, meaning all parameters already have clear descriptions. The tool description adds a summary of the action enum but does not provide additional semantic value beyond what the schema offers. Baseline is 3, which is appropriate here.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states 'Non-lifecycle Line Item operations — get, list, update, duplicate, verify, and create programmatic types,' clearly defining the tool's purpose as CRUD and programmatic creation for line items. It also distinguishes from siblings like 'line_item_lifecycle' and 'campaign', ensuring no ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a 'WHEN TO USE' section that explicitly contrasts this tool with 'campaign' and 'line_item_lifecycle', stating that line_items handles individual CRUD and programmatic creation, while others handle orchestration or status transitions. This provides clear guidance on when to use each tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully carries the burden of behavioral disclosure. It states read-only mode, required OAuth 2.0 authentication, zero credits, and output specifics (URLs expire after 24h, coverage reports). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: one clear introductory sentence followed by key-value lines for mode, auth, credits, output, and usage. Every sentence adds value with no waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (2 params, no output schema), the description adequately covers all necessary context: output format, expiration, and coverage report content. No missing information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description does not add parameter-specific information beyond what the schema already provides (enum values and network code description). It adds output context but not parameter detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'generate' and 'validate' with clear resources 'preview URLs' and 'creative coverage'. It uniquely identifies the tool's function among siblings like 'creatives' or 'campaign', making the purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use the tool ('before launching a campaign to verify all creatives render correctly and coverage is complete') but does not provide explicit when-not-to-use scenarios or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers mode (mixed read/write), auth requirements, credits (0 for writes but modifies config), and side effects (changes affect future campaigns). Could be slightly more explicit about write reversibility, but overall strong.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with sections like MODE, AUTH, OUTPUT, SIDE EFFECTS, and WHEN TO USE. While slightly lengthy, every sentence adds value, and the main purpose is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the two parameters and 100% schema coverage, the description provides complete context for all actions, including output descriptions for key sub-operations. No output schema is needed as the tool returns blueprint JSON.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed enum descriptions. The description adds extra context beyond the schema (e.g., 'Validate with a dry-run before saving to production'), raising the baseline from 3 to 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages the tenant inventory blueprint, specifying it covers ad formats, positions, key-values, and brand settings. It also distinguishes from the 'formats' sibling tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'WHEN TO USE' section explicitly states when to use this tool vs. alternatives (formats tool), providing clear guidance for the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are provided, the description carries the full burden. It discloses the MODE ('mixed (read + write)'), AUTH ('OAuth 2.0 required'), CREDITS ('Reads = 0. Writes = 0 credits (config changes only)'), and OUTPUT structure. It also details the behavioral traits of each sub-operation, including which are read-only, write, or destructive, and the implications of destructive actions (e.g., 'delete_recipe: Destructive write — does not affect existing creatives').
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE). It is front-loaded with the purpose. While it is somewhat long, every sentence adds value, and the bullet points for action types improve readability. However, some repetition of schema content could be trimmed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is complete given the tool's complexity and lack of output schema. It explains the output fields (id, name, dimensions, creative_type, applicable_sites), covers authentication, credits, and sub-operations. It provides enough context for an AI agent to understand when and how to use this tool. The differentiation from siblings adds to completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so the baseline is 3. The description repeats some parameter details (e.g., action enum values) but does not add significant new meaning beyond the schema's descriptions. The schema already explains each action in detail. The description provides a high-level overview but does not significantly enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Manage the Custom Format Registry — reusable creative format recipes with multi-site scope.' It uses a specific verb 'manage' and identifies the resource as creative format recipes. It also distinguishes itself from sibling tools like 'blueprint' and 'creative_assets', providing clear differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use the tool: 'Use formats to define reusable creative format specifications' that can be applied across multiple GAM networks. It also provides explicit scenarios to avoid by stating what it is NOT the same as (blueprint and creative_assets). The 'WHEN TO USE' section provides clear guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description compensates by stating MODE (mixed), AUTH (OAuth 2.0), and CREDITS per operation. It also details return values for get_network_info and list_accessible_networks. However, it does not explicitly mention that switching or updating may have side effects, though those are implied.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE). It is slightly verbose but each sentence adds value. Front-loaded with summary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description thoroughly explains return values and behavior. The tool has only 2 parameters with simple enum, and the description covers all necessary context for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%. The description adds value beyond schema by providing context for network_code ('Obtain via select_gam_network or list_accessible_networks') and detailing each action's purpose and requirements.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool is for 'GAM network management' and lists specific sub-operations: get info, switch, list, update. This distinguishes it from sibling tools that handle different entities like audiences, orders, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a 'WHEN TO USE' paragraph that explicitly explains usage: after authentication, call list_accessible_networks to find networks, then switch_network to set active. It also provides context for each sub-operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It declares read-only mode, OAuth 2.0 requirement, zero credits, and a clear output format (ResultSet with columns and rows). It also states a 1000-row limit. Minor omission: no mention of error handling or timeouts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with labeled sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE, LIMITATIONS) and front-loaded with the main purpose. Every sentence adds information; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 3 parameters and no output schema. The description covers return format, row limit, table references, and alternatives. It could mention pagination or that queries must be SELECT-type, but the read-only flag implies that. Sufficient for the given complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value beyond schema by listing supported tables (Order, LineItem, etc.), providing an example query, and explaining the network_code parameter's scope. This incrementally aids understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Execute PQL queries against GAM reporting tables' with a specific verb and resource. It differentiates from siblings like 'reporting' by stating it's for ad-hoc extraction not covered by structured reports, and explicitly directs users to 'reporting' for structured reports.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use ('ad-hoc data extraction not covered by the reporting tool's structured reports') and when-not-to-use ('For structured delivery/inventory reports, use reporting instead'). It also lists limitations about table availability and known table issues.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite lacking annotations, the description discloses critical behavioral traits: MODE: read-only (safe), AUTH: OAuth 2.0 required, CREDITS: 0 (free), and OUTPUT structure for both actions. This fully informs the agent of what to expect.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE) and is concise. Every sentence provides valuable information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (two sub-operations, no output schema), the description is complete. It covers both actions, describes return structures, states authentication requirements, and provides usage context. No gaps remain for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% coverage with detailed descriptions for both parameters (action with enum, network_code). The description does not add additional semantic meaning beyond what the schema offers, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: inspecting OrbiAds account billing, specifically credit balance and transaction history. It uses a specific verb ('Inspect') and identifies the resource, effectively distinguishing it from sibling tools like 'audit' or 'campaign' which have different domains.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use each sub-operation: 'Call get_credit_balance before write operations to confirm sufficient credits. Use list_transactions for usage auditing.' This clearly states the context and purpose, helping the agent choose correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavior: 'MODE: read-only', 'AUTH: OAuth 2.0 required', 'CREDITS: 0 (free)', and details the output format. This provides complete transparency for a read-only credential check.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured with clear sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE). Every sentence adds value without redundancy. It is front-loaded with the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Although there is no output schema, the description specifies the exact output structure. Combined with auth, mode, and usage guidance, the description is complete for this simple credential-checking tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (one parameter fully described). The description does not add extra meaning beyond the schema; it simply mentions 'network' in the purpose. Baseline 3 is appropriate as the schema already documents the parameter adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Verify that the GAM OAuth credentials for a network are still valid and have required scopes.' It uses a specific verb (verify) and resource (credentials), and distinguishes itself from the sibling tool 'initiate_gam_auth' which handles re-authorization.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly provides a 'WHEN TO USE' section: 'Call at the start of a session to verify credentials before running operations. If valid=false, call initiate_gam_auth to re-authorize.' This gives clear context and directs to an alternative tool when needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description thoroughly discloses mode (destructive), auth requirements, side effects, and irreversibility, giving full 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.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Well-organized with labeled sections, no unnecessary words, and all essential information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers all relevant aspects: purpose, usage, behavior, output format, and side effects. No output schema needed given the explicit output description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema already describes both parameters; the description reinforces the critical role of confirmation_token, adding value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Revoke and permanently remove') and the resource ('GAM OAuth credentials for a network from the tenant'), making it distinct from sibling tools like initiate_gam_auth.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly provides a use case ('end of contract') and notes the requirement of a confirmation token. Could be improved by mentioning alternatives, but the sibling list provides context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses read-only mode, OAuth requirement, free credits, and output format. No annotations to contradict.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with labeled sections, concise yet complete, no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Fully covers purpose, usage, and output for a zero-parameter tool. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters; baseline 4 is appropriate since description doesn't need parameter info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it returns the tenant ID for the authenticated session. Distinct from sibling tools like tenant_catalog.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says to call first in any workflow and explains why the tenant_id is needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, description fully discloses mode (mixed read+write), auth requirements (OAuth), credit costs, output formats for key actions, and side effects (e.g., destructive nature of archive_inactive_ad_units).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Description is compact (~150 words) and well-structured with sections (MODE, AUTH, CREDITS, OUTPUT, SIDE EFFECTS, WHEN TO USE). Every sentence serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of 10 sub-operations and no output schema, the description covers all necessary context: mode, auth, credits, side effects, usage guidance, and output format for key actions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with detailed enum descriptions for each action and network_code parameter. The description text does not add new information beyond summarizing the schema, meeting the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool manages GAM ad unit inventory with specific sub-operations like tree traversal, audit, batch creation. It also distinguishes from sibling tools like targeting and blueprint.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit WHEN TO USE section directs agents to use inventory for ad unit structure, targeting for custom targeting keys, and blueprint for canonical format. Additionally, within action descriptions, it provides chaining instructions (e.g., run find_inactive_ad_units first before archive).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, description fully discloses MODE (mixed), AUTH (OAuth 2.0), CREDITS (reads=0, writes=0.5), and output fields. For each action, it explains behavior, e.g., 'archive_placement' is 'Destructive write — removes from targeting options.'
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Description is well-structured with sections (purpose, MODE/AUTH/CREDITS/OUTPUT, WHEN TO USE). Every sentence adds value; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 2-parameter tool with enum actions, description covers all essential aspects: purpose, behavioral traits, when to use, output structure, and differentiation from siblings. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with detailed enum explanations for action. Description adds no additional parameter semantics beyond what's in the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Manage GAM placements — named groups of ad units for targeting.' It distinguishes from sibling tools by noting 'Use inventory for individual ad unit management' and references targeting tool for line item targeting.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit 'WHEN TO USE' section explains when to use placements (creating named groupings for targeting in line items) and when not (use inventory for individual ad unit management). Provides clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully compensates by including MODE (read-only), AUTH requirements, CREDITS, and OUTPUT format. It clearly sets expectations about side effects and behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with labeled sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE). Every sentence serves a purpose, no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter polling tool with no output schema, the description covers purpose, usage context, behavior, auth, and expected output format completely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds no additional detail beyond the schema's parameter description. The context of use is implied, but no new semantic information is provided for the parameter itself.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Poll the OAuth authorization status after initiating a GAM auth flow', specifying the verb (poll), resource (authorization status), and context (after initiate_gam_auth), distinguishing it from sibling tools like initiate_gam_auth.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly provides 'WHEN TO USE' with specific instructions: 'Call repeatedly (every 2–5 seconds) after initiate_gam_auth until status = \'authorized\' or \'failed\''. This gives clear context and timing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses read-only mode, OAuth 2.0 requirement, zero credits, and internal orchestration behavior. However, it does not mention error handling or limitations, which would make it a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE, Example, NOT). Every sentence adds value, and the key information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with only 2 simple parameters and no output schema, the description covers all essential aspects: purpose, authentication, cost, output format, usage guidance, and relation to sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by explaining that 'goal' is a plain-language description and provides an example of how it is used (e.g., selecting dimensions/metrics automatically), which goes beyond the schema's basic description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is a 'high-level reporting orchestration' tool that accepts natural language goals and returns formatted reports. It distinguishes itself from the sibling 'reporting' tool by noting it is a higher-level orchestrator.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly includes a 'WHEN TO USE' section with an example and contrasts with the sibling tool: 'NOT the same as reporting'. It also shows how the tool internally calls other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description fully disclosures behavioral traits: it is a write operation that changes session state, requires OAuth 2.0, costs 0 credits, and returns a structured output. It also explains the side effect of setting the active network for future calls.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise and well-structured: a single sentence for purpose, followed by metadata lines and usage guidelines. Every sentence provides new information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description includes the output format. It covers purpose, usage, authentication, credits, and side effects, making it complete for this simple state-changing tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description does not add extra meaning for the parameter beyond the schema's 'GAM network code to set as active.' The usage context is helpful but does not enhance parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool sets the active GAM network for the session, with a specific verb (Set) and resource (active GAM network). It distinguishes itself from siblings by focusing on network selection, which is unique among the listed tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'Call after authentication when the tenant has more than one GAM network linked.' Also clarifies that subsequent calls use this network unless overridden, providing clear usage context and exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and excels: it declares read-only mode, OAuth 2.0 auth, zero credit cost, and structured markdown output with severity levels. This far exceeds typical transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections, but somewhat verbose with bullet points that partially duplicate schema information. Still efficient and front-loaded with key facts.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without an output schema, the description fully explains the output format. It also covers authentication, cost, per-action details, prerequisites, and sibling comparisons, leaving no major gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100% with detailed parameter descriptions, the tool description adds valuable usage context and when-to-use guidance for each action, going beyond mere schema repetition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is a proactive audit suite with six sub-actions for quality and compliance analysis. It explicitly distinguishes from sibling tools 'audit' and 'gam_audit', making its unique purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'WHEN TO USE' section provides specific guidance for each sub-action, and the description contrasts audit_skill with similar tools, giving clear criteria for when to choose it over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses write-heavy nature, OAuth requirement, credit costs, confirmation token necessity, side effects (irreversible deployment), and destructive actions (rollback, archive). This goes well beyond minimal disclosure and fully informs the agent of behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with labeled sections (MODE, AUTH, etc.) and front-loaded with the key purpose. It is fairly long but every sentence adds value. Minor redundancy in repeating confirmation token info across sections.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema, the description explicitly states the output format for deploy and rollback. It also covers side effects, destructive actions, and prerequisites. For a complex tool with many sub-operations, this is comprehensive and complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds workflow context (e.g., why confirmation_token is needed, how deploy works) that complements the schema's parameter descriptions. While the schema already details each parameter, the description's additional context justifies a slightly higher score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Orchestrate GAM campaign lifecycle — the primary write surface for creating and managing campaigns.' It uses a specific verb ('orchestrate') and resource ('GAM campaign lifecycle'), and distinguishes itself from sibling tools like line_items and orders by specifying when to use each.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit guidance is provided: 'Use campaign for end-to-end campaign creation from a blueprint. Use line_items or orders for surgical updates to existing campaigns.' This tells the agent when to use this tool versus alternatives, which is exactly what this dimension requires.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the mode (mixed read+write), auth requirement (OAuth 2.0), credit costs (reads=0, writes=0.5), output structure (Creative objects with specific fields), and preview URL expiry. Destructive actions like archive include a warning to run pre_archive_check first.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with labeled sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE, NOTE) and front-loads the main purpose. However, it is slightly verbose in listing action enum options, which are already detailed in the schema, making it somewhat redundant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (multiple actions, LICA management, native styles), the description covers all essential aspects: purpose, usage guidelines, behavioral traits, parameter meanings, and output format. No output schema exists, but the description explains return fields, making it complete for appropriate tool invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by including contextual notes (e.g., 'Run pre_archive_check first' for archive actions) and explaining the relationship between Creative entities and LICAs. While the schema's enum descriptions are comprehensive, the description provides additional context for parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages GAM Creative entities and native styles, covering full lifecycle and LICA management. It uses a specific verb+resource ('Manage GAM Creative entities and native styles') and distinguishes from siblings like creative_assets and creative_qa in the 'WHEN TO USE' section.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly provides when-to-use guidance in the 'WHEN TO USE' section, directing users to creative_assets for raw file uploads and creative_qa for compliance validation. It also explains the relationship between Creative entities, creative_assets, and LICAs, aiding correct tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers behavioral traits: MODE (mixed), AUTH (OAuth 2.0 required), CREDITS (reads 0, writes 0.5), and OUTPUT fields. It also flags destructive actions (archive) and idempotency (find_or_create), providing comprehensive behavioral context beyond what structured fields would offer.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (purpose, mode/auth/credits/output, usage guidance, differentiation). It is informative without being overly verbose, though slightly long. Every sentence earns its place, and key info is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (11 sub-actions), absence of output schema, and no annotations, the description compensates well. It details each action, output fields, and usage context, making it complete for an agent to understand and use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds meaningful context for the 'action' parameter by detailing each enum value with read/write status and requirements (e.g., 'create: Write. Requires advertiserId, name, and traffickerId'). This enhances understanding beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as 'Non-lifecycle Order operations — list, get, create, update, and manage orders.' It differentiates from sibling tools like campaign and order_lifecycle with explicit statements, making the purpose distinct and well-defined.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'WHEN TO USE' section explicitly states when to use this tool ('Use orders for Order entity management') and when not to, naming alternatives ('Use campaign for full campaign orchestration... Use order_lifecycle for status transitions'). This provides clear guidance for an AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
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 MODE (mixed), AUTH (OAuth 2.0 required), CREDITS (reads 0, writes 0.5 credits), OUTPUT (Product objects with fields), and details each sub-operation's nature (read/write/destructive). The archive action is explicitly described as destructive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with headers (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE) and bullet points for actions. It is moderately sized and front-loaded with purpose. Every sentence adds value, though slightly verbose due to detailed action list.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description explains the return format (Product objects with id, name, etc.). It covers all actions, prerequisites for 'create', and references sibling tools. The tool is fairly complex, but the description fully addresses the gaps left by structured fields.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds significant meaning by detailing each enum action with its requirements and the network_code parameter with an example and how to obtain it. However, the schema already documents thoroughly, so a slight bump to 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages GAM Products and Product Packages for programmatic direct deals, specifying the verb 'Manage' and the resource. It distinguishes from sibling tools by mentioning the 'deals' tool for creating deals from products.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides an explicit 'WHEN TO USE' section, stating this tool is for managing the product catalogue for Programmatic Direct deals, and refers to the 'deals' tool for creating deals from products, giving clear context and exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully bears the burden of behavioral disclosure. It clearly states MODE (mixed read+write), AUTH (OAuth 2.0 required), CREDITS (reads 0, writes 0.5), and marks destructive actions (e.g., 'Destructive write'). It also describes output objects and special cases like get_inventory_forecast.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE, NOTE) and each action is described concisely. While it is lengthy, every sentence provides necessary guidance. Slight redundancy in repeating 'Read-only' could be trimmed but overall earns a 4.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of 18 sub-actions and no output schema, the description is complete. It specifies return types (CustomTargetingKey objects, canonical lists), credits, authentication, and prerequisites for destructive actions. No gaps remain for an AI agent to safely invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds significant value beyond the schema by providing usage context for each action (e.g., 'Run inventory find_inactive_ad_units first' for archive_ad_unit) and clarifying scope (e.g., 'Read-only'). This justifies a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Manage GAM custom targeting keys, values, and ad unit targeting configuration.' It uses specific verbs and resources, and the 'WHEN TO USE' section distinguishes it from sibling tools like 'line_items' and 'inventory'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'WHEN TO USE' section explicitly guides when to use this tool versus alternatives: 'Use targeting to manage the custom targeting vocabulary... Use line_items to apply targeting to line items. Use inventory for ad unit structure.' Additionally, individual action descriptions note alternatives, e.g., 'For full hierarchy, use inventory get_ad_unit_tree'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers behavioral traits: declares MODE (mixed read+write), AUTH (OAuth 2.0), CREDITS (free list/get; create costs 0.5 credits and needs confirmation_token), OUTPUT (returns segments with specific fields), and SIDE EFFECTS (modifies data, can activate/deactivate). No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (MODE, AUTH, CREDITS, OUTPUT, SIDE EFFECTS, WHEN TO USE) and each sentence provides relevant information. It is comprehensive but not overly verbose, earning high marks with a slight deduction for its length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (multiple actions, two parameters, no output schema), the description is remarkably complete. It covers usage context, authentication, credits, side effects, and output format. The only minor omission is a concrete example of confirmation_token handling, but overall it meets the needs for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters. The description adds significant value: for the action parameter, it details each enum value's behavior (read/write, cost, required sub-params). For network_code, it explains its purpose and how to obtain it. This goes well beyond the schema's minimal description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Manage GAM first-party audience segments' which is a specific verb+resource. It distinguishes from sibling tools by explicitly noting that for targeting segments on line items, one should use the targeting tool instead.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides a dedicated 'WHEN TO USE' section explaining when to use this tool (managing first-party data segments) and when not (use targeting tool). Also mentions AUTH requirements (initiate_gam_auth first) and CREDIT costs, giving clear context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: 'MODE: read-only (all actions are non-destructive analysis)', 'AUTH: OAuth 2.0 required', 'CREDITS: 0 (all free)', and output format explained. Each sub-action's behavior is detailed in enum descriptions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a brief intro, metadata in key-value pairs, usage guidelines, and differentiation. It is slightly lengthy but each sentence adds value; the structure aids readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema, the description explains the output. It covers purpose, usage, auth, credits, output, and sub-actions thoroughly. All necessary context for an agent to select and invoke the tool correctly is present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and description adds value: action enum values have detailed descriptions, and network_code includes example and source instructions. The overall description also provides context that enhances parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Creative quality assurance — validate, scan, and pre-check creatives before and after trafficking' and lists specific actions via enum. It distinguishes from sibling 'audit_skill' by specifying that audit_skill checks network-wide health while creative_qa focuses on individual creative compliance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit usage guidance: 'Run creative_qa after uploading creative assets and before activating line items. Use pre_archive_check before archiving a creative to detect active associations.' Also notes that it is not the same as audit_skill, providing clear when-to-use and when-not-to-use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses the tool's read-only mode, required OAuth 2.0 authentication, zero credit cost, and the structure of the markdown output report including pass/fail verdict. It also explains it is a wrapper calling three sub-tools.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-organized with labeled sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE) and clear differentiators. Every sentence serves a purpose without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately describes the output (comprehensive markdown report with three sections and verdict). It also explains the tool's role as a convenience wrapper and differentiates it from related tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by stating the default value for the framework parameter ('Defaults to orbiads_baseline if omitted'), which is not in the schema. However, it does not provide additional semantic context beyond what the schema already offers.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it runs a full GAM network compliance audit combining hygiene, diagnostics, and standards baseline. It distinguishes itself from siblings audit and audit_skill with explicit 'NOT the same' statements.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a 'WHEN TO USE' section that advises using this tool for a complete one-shot audit and directs to audit_skill for individual components. It also clarifies the difference from audit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: read-only mode, OAuth 2.0 requirement, free credits, output structure (Job objects with id, type, status, progress, result_url, error), and recommended poll interval of 5 seconds.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with labeled sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE), is front-loaded with the purpose, and every sentence adds value. Length is appropriate for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema or annotations, the description is thorough: it covers all sub-operations, authentication, output format, usage context, and even credits. No critical information is missing for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions, but the description adds meaningful context beyond the schema, such as the recommended polling interval for 'poll' and how to obtain network_code. This enhances usability without being redundant.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as managing async GAM background jobs, specifying 'Poll and manage async GAM background jobs.' It differentiates from the sibling 'jobs' tool by noting that jobs are created by other tools and this is read-only polling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes an explicit 'WHEN TO USE' section advising to use after starting a long-running operation and poll until completion. It also details the four sub-actions (poll, get, list, cancel) with their contexts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Discloses destructive nature of archive, OAuth 2.0 requirement, 0.5 credits, output structure, and confirmation token necessity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise, each sentence adds value. Front-loaded with key info, uses bullet points for clarity, and avoids unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description includes output structure. Covers auth, credits, destructive action, and prerequisite for archive. Complete for a lifecycle tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with clear descriptions. Description adds context like confirmation token from estimate_cost call, but schema already provides good understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it performs lifecycle status transitions (activate, pause, archive, resume) on a GAM Line Item. Distinguishes from sibling tool 'line_items' which is for data updates.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use: only for status transitions. For data updates, use line_items update action. Also mentions confirmation token requirement for archive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description fully shoulders the transparency burden. It declares MODE: write, AUTH: OAuth 2.0 required, CREDITS: 0.5 credits, and OUTPUT: returns {order_id, previous_status, new_status}. It also flags the destructive nature: 'DESTRUCTIVE: archive stops all line item delivery under the order.' This covers mutation, authentication, cost, return format, and side effects thoroughly.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, using a structured format with labeled sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE, DESTRUCTIVE). Every sentence adds value—no fluff, and the most critical information is front-loaded in the first line.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool involves mutation with 4 parameters and no output schema. The description covers all essential aspects: purpose, when to use, authentication requirements, credit cost, return format, and destructive consequences. It leaves no significant gaps for an agent to interpret.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, providing detailed descriptions for each parameter, including enum options and required fields. The description adds context about confirmation_token being required for archive and the destructive nature of archive, which enhances understanding beyond the schema. With full schema coverage, the additional description justifies a score above baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description starts with 'Perform lifecycle status transitions on a GAM Order (approve, archive, disapprove).' It clearly states the specific actions and the resource (GAM Order), distinguishing it from sibling tools like line_item_lifecycle or orders.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Includes a 'WHEN TO USE' section that explicitly states 'Use this for order status transitions. For data updates, use the orders update action.' This provides clear context and an alternative, helping the agent decide 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.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description fully discloses behavioral traits: it states the mode (mixed read+write) and categorizes actions, details side effects (e.g., irreversible delete for templates, soft-delete for GAM reports, quota implications), lists authentication and credit requirements, describes output formats, and notes limitations (rejected SOAP-era metrics/dimensions). No contradictions with annotations (none provided).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (intro, MODE, AUTH, CREDITS, OUTPUT, SIDE EFFECTS, WHEN TO USE, LIMITATIONS). It is front-loaded with the overall purpose, and every sentence adds necessary information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (30+ actions), the description comprehensively covers all aspects: purpose, read/write mode, authentication, credits, output formats, side effects, usage guidelines, and limitations. No output schema exists, but the OUTPUT section adequately explains return types. The description is complete for an AI agent to correctly select and invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by providing strategic guidance on parameter usage for forecasting (e.g., 'For pre-flight feasibility, pass sizes/creativeSizes...'). This extra context justifies a score of 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool covers 'Full GAM and GA4 reporting' including delivery reports, custom reports, forecasting, traffic data, billing, and report management. It distinguishes from sibling 'reporting_skill' by specifying when to use each tool, making the purpose and scope unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'WHEN TO USE' section explicitly states to use this tool for all data extraction and analysis, and 'reporting_skill' for high-level multi-step workflows. It also provides specific use cases for delivery analysis, custom reports, forecasting, etc., including detailed advice for forecasting parameters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even without annotations, the description discloses behavioral traits: MODE: read, AUTH: OAuth 2.0 required, CREDITS: 0 (free), and explains that scanning triggers a background job. It also describes the output of two sub-operations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with sections (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE) and front-loaded with the main purpose. Every sentence adds value without redundancy. It is concise yet comprehensive.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (multiple actions, background job, caching), the description covers authentication, credits, usage patterns, and expected outputs for the two main sub-operations. Despite no output schema, the description compensates adequately. Sibling tools are listed, adding context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the baseline is 3. The description adds value by explaining the sub-operations in context and providing usage patterns (e.g., 'Poll with get_scan_status'). It also clarifies that network_code is required for network-scoped operations.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool's purpose: 'Scan and cache the tenant's GAM inventory catalog for fast downstream operations.' It uses specific verbs ('Scan and cache') and clearly distinguishes itself from sibling tools by noting that other tools use the catalog for fast lookups.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use instructions: 'Run scan_network once after connecting a new GAM network, then call refresh periodically (daily) to keep the catalog current.' It also explains that other tools depend on this catalog, implying when not to use alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description discloses mode (write), auth requirements, credits (free), output format (auth_url, session_id), and the need to poll poll_auth_status. All behavioral aspects are communicated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with headings (MODE, AUTH, CREDITS, OUTPUT, WHEN TO USE) and every sentence is informative. No waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains the output and follow-up steps. It also references dependent tools and prerequisites, making the tool's role in the broader workflow clear.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter network_code has a helpful description in both schema and tool description, including how to obtain it ('from the GAM UI or list_accessible_networks'). Schema coverage is 100%, and the description adds value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Start the OAuth 2.0 authorization flow to link a GAM network to the OrbiAds tenant.' It uses a specific verb and resource, and distinguishes from sibling tools like check_credentials and poll_auth_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use ('when a GAM network has not yet been authorized (check_credentials returns false)') and when not to ('Do not call if credentials are already valid').
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
GitHub Badge
Glama performs regular codebase and documentation scans to:
- Confirm that the MCP server is working as expected.
- Confirm that there are no obvious security issues.
- Evaluate tool definition quality.
Our badge communicates server capabilities, safety, and installation instructions.
Card Badge
Copy to your README.md:
Score Badge
Copy to your README.md:
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/OrbiAds/Orbiads-GAM-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server