CreativeScope — Mobile Game Ad Creative Intelligence

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 details that the tool uses vector-neighbor search, excludes low-similarity and near-duplicates, does not expose raw similarity scores, and describes internal resolution for Chinese queries. It also explains the proxy seed limitation.

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, information-dense paragraph. It front-loads the core function and includes necessary details. While it could be broken into sections for readability, every sentence contributes meaning, and there is no redundancy. Still concise for the amount of 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 no output schema, the description covers return behavior (ordered by similarity, exclusions, no raw scores), all parameters, and multiple use cases (with/without creative_id, English/Chinese). It is fully complete for the tool's complexity.

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

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

Schema coverage is 100%, so baseline is 3. The description adds significant context beyond the schema: it clarifies the relationship between query and creative_id, explains that query is used to select a seed, and specifies the maximum limit. It also provides domain-specific guidance (e.g., English terms only). This adds value, warranting a 4.

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 finds visually similar creatives using the stored vector of an existing creative. It uses a specific verb ('find') and resource ('similar creatives'), and distinguishes from sibling tools like search_creatives by specifying vector-based similarity and visual similarity.

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

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

The description provides explicit guidance: when to supply creative_id vs query, how to handle English vs Chinese concepts, and what to do with results (e.g., disclose proxy seeds). It implies when not to use (e.g., if exact match needed, use search_creatives) and differentiates from siblings.

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

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

No annotations exist, so the description carries the burden. It discloses that 'Creative tag fields are normalized to English in the result' but does not mention nondestructive nature, authentication, rate limits, or output structure. Adequate but minimal.

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

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

The description is two sentences plus an example, all front-loaded and concise. Every sentence adds value: purpose, use cases, and a concrete example. No wasted words.

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

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

With 6 parameters and no output schema, the description provides adequate context for basic usage (use cases, example) but lacks detail on what a 'brief' contains or the output format. Leaves some uncertainty for the agent.

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

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

Schema description coverage is 100%; parameter descriptions in the schema already explain each field. The description adds marginal value by showing usage in the example, but does not deepen meaning beyond the schema. Baseline 3 is appropriate.

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

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

The description states a specific verb+resource: 'Generate a compact creative brief from recent high-signal mobile game ads.' It clearly distinguishes from siblings like search_creatives or get_creative_detail by focusing on brief generation.

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 lists explicit use cases: 'weekly inspiration, hook mining, competitor creative planning, and UA brainstorming.' It provides an example ('Create this week's puzzle-game creative brief for Facebook') but does not exclude alternative tools 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?

No annotations are provided, so the description carries the full burden. It mentions that creative tag fields are normalized to English, which is a useful behavioral trait. However, it does not disclose whether the operation is read-only, or any potential side effects, rate limits, or authentication requirements. For a read-only profile tool, this is adequate but not comprehensive.

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

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

The description is two sentences and an example, with no wasted words. It is front-loaded with the core purpose, then details and an illustrative question. Every sentence earns its place.

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

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

For a simple tool with one parameter and no output schema, the description lists the main fields (ad activity, creative volume, target countries, platforms) and notes a data transformation (normalization). This is sufficient for an agent to understand the return value. However, it does not mention whether the response is a single object or a list, or if there are pagination limits. The example helps contextualize the use case.

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

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

Schema coverage is 100% and the schema description for advertiser_id is clear (sourced from search_advertisers or creative results). The tool description does not add any additional 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.

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

The description clearly states it gets a profile for an advertiser or game, listing specific included fields (ad activity, creative volume, target countries, platforms). It distinguishes from siblings like search_advertisers (which returns a list) and get_creative_detail (for a specific creative).

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 an example question ('Which markets and platforms is this game scaling on?') that implies a use case, but it does not explicitly state when to use this tool versus alternatives like search_advertisers or get_creative_detail. No when-not or exclusion criteria are 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?

No annotations are provided, so the description carries the full burden. It describes the tool as retrieving data (read operation), but does not explicitly confirm it is read-only, idempotent, or safe. It also omits any authentication, rate limit, or side effect details. The description is adequate but not fully transparent.

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

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

The description is extremely concise at two sentences, with no wasted words. The first sentence states the function and key outputs, and the second provides a concrete example. Front-loading is effective.

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

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

Given the tool's simplicity (one parameter, no output schema), the description covers the main purpose and sample outputs. However, it lacks information about the return format or structure, and the phrase 'English creative insights' could imply language constraints that are not explained. Overall, it is mostly complete but leaves minor gaps.

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

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

The input schema has 100% coverage for the single parameter creative_id, with a description in the schema. The tool description adds value by specifying where the creative_id comes from (search_creatives, find_similar_creatives, or get_creative_rankings), which helps the agent understand valid inputs beyond the schema.

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

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

The description clearly states the tool retrieves 'one creative's delivery metadata and English creative insights' and lists specific data points like opening hook signals and scene descriptions. It distinguishes from sibling tools such as get_creative_rankings which focus on rankings, and search_creatives which is a search tool.

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

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

Usage is implied through the example question 'Why does this winning creative work?', suggesting it is used for deep analysis of a specific creative. However, there is no explicit guidance on when to use this tool over alternatives like find_similar_creatives or get_creative_rankings, nor any conditions 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?

Given no annotations, description discloses key behaviors: platform/country filters unsupported, evergreen monthly-only, day/week normalized to month with disclosure in request_echo, creative tags normalized to English. Missing details on return format or pagination, but for a read-only ranking tool, this is adequate.

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

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

Front-loaded with purpose, then constraints, usage guidance, and an example. Each sentence adds unique value with no redundancy. Slightly long but efficient for the information density.

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

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

No output schema, and description does not explain the return structure (e.g., fields returned, ranking order). While the tool is straightforward, the missing output format could hinder agent understanding. Otherwise, covers constraints and usage well.

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

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

Schema coverage is 100% with descriptions. Description adds context: period normalization for evergreen, genre in original language (Chinese expansion internal), limit maximum 20. These details go beyond the raw schema definitions.

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

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

Description clearly states it gets global or genre-level rising or evergreen creative rankings by day, week, or month. The verb 'get' and resource 'creative rankings' are specific, and the scope is explicitly defined, distinguishing it from siblings like search_creatives.

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

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

Explicitly says when to use (e.g., 'what's rising this week') and when not to use (platform/country filtering), and provides an alternative: 'use search_creatives'. Also warns against mislabeling results as official rankings.

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?

Given no annotations, the description carries full burden. It discloses store platform exclusions (iPad), date range defaults and max, and ranking type definitions. However, it omits any mention of side effects, authentication requirements, read-only nature, or behavior for missing game IDs. This is adequate but not thorough.

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

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

The description is concise with three sentences, no redundant information, and a clear front-loaded purpose. Every sentence adds necessary context without excess.

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 lacking an output schema, the description explains the return structure (dimensions with rank metrics). It mentions the limit parameter but doesn't specify pagination or ordering. For a simple list tool, this is mostly complete but could be slightly more detailed on edge cases.

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 100% schema description coverage, the baseline is 3. The description adds value by clarifying store coverage (only Google Play and iPhone App Store, iPad excluded) and explaining ranking types more explicitly. This exceeds what the schema provides, earning a 4.

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 lists countries, categories, stores, and ranking types where a game appeared on a chart within a date range. It specifies the returned metrics (best rank, latest rank, ranked-day count) and distinguishes from siblings like get_game_rank_trend by focusing on observed dimensions rather than trends.

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 implicit usage context (date range limits, store exclusions) but lacks explicit guidance on when to use this tool versus alternatives like get_game_rank_trend or search_advertisers. No when-not-to-use or alternative tool references are 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?

No annotations provided, so description carries full burden. It discloses return fields (rank series, best/latest rank, country, category, store), modes, supported stores, and date constraints. Lacks explicit read-only hint but implied.

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

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

Three sentences, each essential. First sentence states purpose, second explains modes, third lists supported stores and date constraints. No redundancy.

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

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

Given 8 parameters and no output schema or annotations, the description fully explains all parameter behaviors, defaults, constraints, and return value structure. No gaps.

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

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

Schema coverage is 100%, baseline 3. Description adds value by explaining how parameters interact (e.g., country/category used in exact mode) and defaults. Goes beyond schema.

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

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

Description starts with a clear verb+resource: 'Get one mobile game's daily app-store ranking performance over a date range.' It specifies what is returned and distinguishes from sibling tools like get_game_rank_markets by focusing on trend 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?

Explains two modes (best vs exact) with explicit guidance on when to use each. Also covers default date range and maximum range. Does not explicitly list alternatives from siblings, but context is sufficient.

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

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

No annotations provided, so the description carries the burden. It adds value by disclosing behavior for running jobs (returns polling guidance). However, it does not cover auth needs, rate limits, or other 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?

Two sentences; the first states the core purpose, the second adds a behavioral note and example. Front-loaded and efficient with no wasted words.

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

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

For a simple retrieval tool with two parameters and no output schema, the description covers purpose, edge case handling, and usage example. It is nearly complete, though lacking mention of response format or pagination.

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

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

Schema coverage is 100% with parameter descriptions. The description adds an example but does not enhance meaning beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool retrieves completed reference-image search results, with a specific example. It distinguishes from sibling tools like submit_reference_image_search and get_reference_image_search_status.

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

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

The description mentions that if the job is still running, it returns polling guidance, implying usage for both completed and in-progress jobs. However, it does not explicitly state when not to use or mention alternatives like get_reference_image_search_status for status checking.

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

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

No annotations are provided, so the description carries full burden. It states the tool gets 'processing status' but does not disclose possible status values, whether it's read-only, or any other behavioral traits. While adequate for a simple poll, it lacks extra context that would help an agent.

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

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

Two concise sentences: a clear statement and an example question. No unnecessary text, front-loaded with 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?

For a simple one-parameter polling tool without an output schema, the description is fairly complete. It explains the purpose and parameter. However, it could mention possible status outcomes for better 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?

The input schema has 100% coverage with a description for job_id. The description adds an example question but no additional semantics beyond what the schema provides. Baseline 3 is appropriate.

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

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

The description clearly states 'Get the processing status of a reference-image search job' and provides an example question, making the purpose specific and distinct from sibling tools like submit_reference_image_search.

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 polling job status via the example, but does not explicitly state when to use this tool vs alternatives or when not to use it. No exclusions or alternatives mentioned.

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

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

No annotations are provided, so the description fully carries the burden. It mentions search by name and optional filters, but does not disclose rate limits, result format, pagination, authentication needs, or behavior when no results are found. The parameter 'limit' (max 20) is only in the schema.

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

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

The description is extremely concise: two sentences plus an example. It front-loads the action, wastes no words, and every sentence adds value.

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 brief. It does not explain the structure of results (e.g., list of advertisers, fields), pagination, or error conditions. The hint to use get_advertiser_profile partially compensates, but more detail would be helpful for an agent.

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

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

Schema description coverage is 100%, so baseline is 3. The description repeats the filter categories (genre, region, platform) but does not add substantial meaning beyond what the schema provides. The mention of using the returned advertiser_id is context for the output, not 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?

Clearly states it searches for advertisers, game studios, or mobile games by name and optional filters. Distinguishes from sibling tools like search_creatives (searches creatives) and get_advertiser_profile (retrieves details for a given ID), with a hint to use the returned ID with that tool.

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

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

Provides an example query and suggests using the returned advertiser_id with get_advertiser_profile, but does not explicitly state when this tool is preferred over siblings or when not to use it (e.g., for creative searches use search_creatives).

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

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

With no annotations, the description fully discloses internal Chinese source-label expansion, that results include media_url and normalized English tags, and prohibits user-generated translations. No contradictions detected.

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

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

The description is concise: two sentences plus an example. Every sentence adds essential information: purpose, internal behavior, use cases, output features, and example. No redundancy or fluff.

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 8 parameters, 100% schema coverage, no output schema, the description covers usage context, internal processing, and output traits (media_url, normalized tags). It lacks details on other result fields but is sufficient for a search tool.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the internal expansion rule and giving an example query, clarifying how to use the 'query' parameter and the role of 'genre'.

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 (search) and resource (mobile game ad creatives), specifies query methods (keyword or natural language), and provides an example. This distinguishes it from siblings like find_similar_creatives or get_creative_detail.

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

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

The description explicitly lists use cases (UGC-style ads, winning creatives, etc.) and provides an example query. It also warns against inserting Chinese translations into the English query. However, it does not explicitly contrast with alternative tools like find_similar_creatives.

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?

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It explains that the job is asynchronous, lists possible error types (IMAGE_FETCH_FAILED, INVALID_IMAGE, EMBEDDING_MODEL_ERROR), and describes genre normalization and visual-only fallback behavior. Missing details like expected latency or polling mechanism, but sufficient for understanding key behaviors.

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 paragraph of four sentences, front-loading the main action and usage context. Every sentence adds value: purpose, usage condition, constraints/failures, and special behavior (fallback). No filler or redundancy.

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

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

Given the tool's complexity (async job, multiple failure modes, genre normalization) and no output schema, the description provides sufficient context. It covers input requirements, processing behavior, and fallback logic. It could mention how to retrieve results (sibling tools) but is otherwise complete for a submission tool.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds meaningful context beyond schema by explaining async processing, failure modes, and fallback behavior. It does not expand on individual parameters beyond what the schema already provides, but enhances overall understanding of parameter usage.

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

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

The description clearly states the action ('Submit a reference-image similarity search') and the resource (asynchronous job). It distinguishes itself from sibling tools like 'get_reference_image_search_results' and 'get_reference_image_search_status' by specifying it is the submission step.

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

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

The description provides explicit conditions for use: 'when the user provides a directly downloadable public HTTPS image URL.' It also states what is not supported (HTML pages, local paths, base64). However, it does not mention when to use alternatives like 'find_similar_creatives' or when to avoid this tool.

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