OpenAI Ads MCP

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

Annotations already convey read-only, idempotent, and non-destructive behavior. The description adds 'deterministic', reinforcing idempotency. However, it does not explain what 'drafting' entails operationally, whether the results are cached, or any side effects of repeated calls. Given the strong annotation coverage, the description adds some but not extensive behavioral context.

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

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

A single sentence that is concise and to the point. It efficiently communicates the core purpose and inputs. However, it omits necessary detail (e.g., output description, parameter formats) that could be added without significant verbosity. The structure is acceptable for a simple tool but front-loads the essential information.

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

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

Given 4 parameters, 0% schema description coverage, and no output schema, the description is insufficient. It does not explain what 'context_hints' are, how they relate to an ad group, or what the tool returns. A user would likely need additional documentation to understand the tool's full behavior and inputs.

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

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

Schema coverage is 0%, so the description must compensate. It lists the four parameter names (product, audience, intent, keywords) but provides no additional semantics: no data types, formats, allowed values, or examples. 'keywords' has an empty JSON schema type (likely an object) but is not clarified. The parameter names are somewhat self-explanatory, but the description fails to add meaningful detail beyond the names.

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

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

The verb 'draft' and resource 'context_hints' clearly indicate the action and output. The description specifies inputs from product, audience, intent, and keywords, making the core function unambiguous. However, it does not differentiate from sibling tools like 'get_ad_group' or 'manage_conversions', though the scope is distinct enough.

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

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

No guidance on when to use this tool versus alternatives. The description lacks context about prerequisites, typical workflows, or scenarios where drafting context hints is appropriate. Sibling tools exist (e.g., 'get_ad_group', 'manage_conversions') but no comparisons are provided.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that it reads specific fields and verifies API key functionality, which provides useful behavioral context beyond annotations. 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.

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

Single sentence that front-loads the action ('Get the authenticated OpenAI Ads account') and succinctly covers purpose, usage, and return details. Every word earns its place.

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

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

Given zero parameters, rich annotations, and no output schema, the description fully covers what the tool does, what it returns, and its recommended context (first use). Completely adequate.

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

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

No parameters exist, and schema coverage is 100%. The description does not need to add parameter semantics. Baseline 4 is appropriate for zero-parameter tools.

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

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

The description clearly states the tool gets the authenticated OpenAI Ads account and lists specific fields (id, name, timezone, currency, settings). It distinguishes itself from sibling tools by suggesting using this first for API key verification and account reading.

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

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

Explicitly advises to use this tool first to verify API key and read account info. While no direct alternatives or exclusions are given, the instruction to use it first provides clear context. A score of 4 reflects this clarity with room for more specific when-not guidance.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety. The description adds useful context about the returned fields (review_status, creative metadata), but does not go beyond that.

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

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

Single sentence with no redundant words. Perfectly concise and front-loaded.

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

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

For a simple read tool with one parameter and no output schema, the description covers the key purpose and return fields. It is complete enough given the annotations and low complexity.

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

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

Schema description coverage is 0%, meaning no parameter descriptions in schema. The description only says 'by id', which adds no new meaning beyond the schema's ad_id property. No format, constraints, or examples provided.

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

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

The description clearly states the action (Get), the resource (one ad by id), and the specific fields returned (review_status and creative metadata). It distinguishes from sibling tools like list_ads which return multiple ads.

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

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

No guidance on when to use this tool versus alternatives (e.g., list_ads for multiple ads, get_ad_group for ad groups). The description does not mention prerequisites or 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.

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. However, the description adds no additional behavioral context beyond the annotated read-only nature; it does not mention rate limits, auth requirements, or what happens if the ID is not found.

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

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

The description is a single sentence, front-loaded with the verb and resource, and contains no unnecessary words. Every word earns its place.

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

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

Complexity is low (one parameter, get by ID), but without an output schema, the description should clarify what is returned (e.g., the ad group object, null if not found). It does not address edge cases or error handling, leaving the agent with incomplete information.

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

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

Schema description coverage is 0%, but the description mentions 'by id', which clarifies that the required parameter 'ad_group_id' is the identifier. This adds some meaning, but does not provide format, constraints, or examples, leaving the agent with minimal guidance.

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

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

The description 'Get one ad group by id' uses a specific verb ('Get') and resource ('ad group'), clearly distinguishing it from sibling tools like 'list_ad_groups' which list multiple, and other 'get_' tools by resource name.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention that this should be used when a single ad group is needed by ID, nor does it exclude cases where list_ad_groups would be more appropriate.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds no behavioral traits beyond the basic action, such as error handling or permissions needed.

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

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

Single, front-loaded sentence with no wasted words. Efficient and direct.

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

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

For a simple lookup tool with one parameter and no output schema, the description is minimally adequate. However, it lacks details on return format, error cases, or parameter validation.

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

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

With 0% schema description coverage, the description should compensate but only mentions 'by id', not explaining the parameter's format or constraints. The schema provides type and required status, but no additional semantic value.

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

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

The description clearly states the verb 'Get' and the resource 'custom audience by id'. It effectively distinguishes from sibling tools like 'list_audiences' that retrieve multiple records.

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

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

No explicit guidance on when to use this tool versus alternatives. While the name and description imply single retrieval, there is no mention of when to prefer this over 'list_audiences' or other tools.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds minimal behavioral context beyond the parameter usage ('by id'). It does not contradict annotations, but adds little new insight.

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

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

The description is a single, concise sentence with no unnecessary words. It is front-loaded with the core action and resource.

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

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

Given the simplicity of the tool (one parameter, no output schema, extensive annotations), the description is mostly complete. It could mention return value or error behavior, but is sufficient for a straightforward get-by-id operation.

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

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

The schema description coverage is 0%, but the description implies that campaign_id is the identifier via 'by id'. It adds some meaning beyond the schema type, but does not elaborate on format, source, or requirements for the parameter.

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

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

The description 'Get one campaign by id.' clearly specifies the action (get), the resource (campaign), and the method (by id). It distinguishes itself from sibling tools like list_campaigns which retrieves multiple campaigns, and other get_* tools for different resources.

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

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

No usage guidelines are provided. The description does not mention when to use this tool versus alternatives such as list_campaigns for multiple campaigns or other get_* tools. It lacks context on prerequisites or scenarios.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds context about cursor pagination and supported features (segments, time ranges), but does not cover other behavioral traits such as rate limits, data freshness, or authorization requirements. With annotations, the bar is lower, and the description provides moderate added value.

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

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

The description is a single sentence that immediately states the purpose and lists supported features. It is concise, front-loaded, and contains no superfluous information.

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

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

With no output schema and 15 parameters, the description is too high-level. It does not explain the response format, aggregation behavior, or how parameters interact. For a complex tool, more detail is needed to ensure proper agent usage.

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

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

Schema description coverage is 0%, so the description must compensate. It mentions high-level parameter categories (fields, filters, sort, segments, time ranges, pagination) but does not map them to the actual schema parameter names or provide detailed semantics for each of the 15 parameters. This is insufficient for a tool with many parameters.

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

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

The description clearly states the verb 'Get' and resource 'performance insights' for specific scopes (account, campaign, ad group, ad). It distinguishes from sibling tools that retrieve single entities (e.g., get_account, get_campaign) by focusing on aggregated performance data.

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

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

The description implies usage for retrieving performance insights with various parameters like fields, filters, sort, and pagination, but does not explicitly state when to use this tool versus alternatives like get_campaign or list_campaigns. It lacks when-not or alternative tool references.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the description adds no behavioral context beyond what annotations provide. It does not mention pagination, filtering, or any other behavioral traits.

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

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

The description is very short (6 words) and front-loaded, but it lacks sufficient detail for a tool with 5 parameters. While concise, it sacrifices necessary information.

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

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

Given the tool has 5 parameters and no output schema, the description is severely incomplete. It does not describe return values, filtering capabilities, or any usage context. It fails to meet the needs of an agent selecting and invoking this tool.

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

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

Schema description coverage is 0%, but the description does not explain any of the 5 parameters. It fails to compensate for the low coverage, providing no added meaning about parameters like 'after', 'before', 'limit', 'order', or 'campaign_id'.

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

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

The description clearly states the verb 'list', the resource 'ad groups', and the scope 'for a campaign'. It distinguishes from sibling tools like 'get_ad_group' (single) and 'list_ads' (different resource).

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

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

The description provides no guidance on when to use this tool vs alternatives, no prerequisites, and no exclusion criteria. It is a bare statement without contextual cues.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. Description adds no extra behavioral context (e.g., pagination details, result format). Without contradiction, a 3 is appropriate as it doesn't harm but adds no value beyond annotations.

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

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

The single sentence is concise and front-loaded, but at the expense of necessary detail. It earns its place but omits critical context, making it borderline adequate.

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

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

Given 5 parameters with zero schema description, no output schema, and siblings providing alternatives, the description is incomplete. Annotations are rich but insufficient to make the tool fully usable without guessing parameter semantics.

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

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

With 0% schema description coverage, the description must explain parameter meanings (ad_group_id, after, limit, order, before). It only mentions 'in an ad group', leaving four parameters (including pagination cursors and ordering) completely unexplained, failing to compensate for schema gaps.

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

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

The description 'List ads in an ad group.' is specific with a clear verb ('List') and resource ('ads') within a context, effectively distinguishing from siblings like 'get_ad' (singular) and 'list_ad_groups' (different resource).

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

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

No guidance on when to use this tool versus alternatives such as 'get_ad' for a single ad or other listing tools. Lacks explicit context, exclusions, or prerequisites.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds no further behavioral context (e.g., pagination behavior, account scoping specifics), but with strong annotations, a baseline score of 3 is appropriate.

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

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

The description is a single sentence with no unnecessary words. It efficiently conveys the core purpose.

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

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

Despite annotations covering safety, the description omits crucial operational details such as pagination (e.g., cursor-based or offset), default ordering, and the structure of the returned audience list. With no output schema, the agent has insufficient information to handle the response.

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

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

Schema description coverage is 0%, meaning none of the 4 parameters (after, limit, order, before) are documented in the schema. The tool description does not explain any parameter meanings, leaving the agent without guidance on how to use them correctly.

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

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

The description specifies the verb 'list', the resource 'custom audiences', and the scope 'for the authenticated ad account'. It clearly distinguishes from sibling tools like get_audience (which retrieves a single audience) and others that operate on different resources.

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

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

No guidance is provided on when to use this tool versus alternatives like search_geo or get_audience. There is no mention of prerequisites, exclusions, or best-use scenarios.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety. The description adds cursor pagination behavior, which is useful beyond annotations.

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

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

Single sentence, no fluff, front-loaded with key information.

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

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

Given 4 parameters with no schema descriptions and no output schema, the description is too sparse; lacks details on return format, filtering, ordering defaults, and pagination limits.

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

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

With 0% schema coverage, description barely helps: only mentions 'cursor pagination' implying after/before and limit, but does not explain order or parameter specifics.

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

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

Description explicitly states the action (list), resource (campaigns), scope (authenticated ad account), and mentions cursor pagination, distinguishing it from single-resource siblings like get_campaign.

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

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

Description implies usage for listing campaigns, but provides no explicit guidance on when not to use or alternatives (e.g., get_campaign for a single campaign).

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

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

The description uses 'manage' which implies write operations, but annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. This is a clear contradiction since the schema includes create and set actions, which are mutations. The description misleads about the tool's behavior.

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

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

The description is a single short sentence, but it lacks important structural elements. It does not front-load the key action parameter or state that this is a multi-action tool. Being concise is not helpful if it omits critical information.

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

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

Given the tool's complexity (14 parameters, multiple actions, no output schema), the description is grossly incomplete. It fails to explain any action behaviors, parameter dependencies, or return values.

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

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

With 0% schema description coverage, the description should explain key parameters. It does not mention any of the 14 parameters, including the required 'action' parameter or how it affects behavior. No value is added beyond the schema structure.

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

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

The description states the verb 'manage' and lists several conversion-related resources (pixels, API keys, event settings, reporting), but it does not clarify that the tool performs different actions based on the 'action' parameter. It is clear enough to indicate the broad domain but lacks specificity.

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

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

The description provides no guidance on when to use this tool versus sibling tools like get_insights, get_account, etc. No context about when to choose manage_conversions over other tools is given.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, giving a good behavioral baseline. The description adds that it returns IDs usable in campaign targeting, which is useful context but does not disclose additional traits like authentication needs, rate limits, or output format.

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

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

The description is a single sentence with 14 words, highly concise. It front-loads the verb and resource, and every word contributes to the purpose.

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

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

Given the tool has one parameter, no output schema, and comprehensive annotations, the description covers the essential purpose. However, it lacks details about the output structure (e.g., format of IDs) and any limitations, which would be helpful for completeness.

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

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

With 0% schema description coverage, the description must compensate. It states that the 'query' parameter is for searching geo targets, implying it is a search term. However, it does not specify expected format, length, or examples, so it adds moderate meaning but not complete clarity.

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

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

The description clearly states the verb 'Search' and the resource 'geo targets', and specifies the purpose: to return IDs usable in campaign targeting for 'targeting.locations.include'. It distinguishes from siblings which deal with ads, campaigns, etc., and not geo targets.

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

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

The description implies the tool is for obtaining geo IDs for campaign targeting, but it does not provide explicit guidance on when to use versus alternatives, nor does it mention exclusions or prerequisites. Usage context is implied but not fully explicit.

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