Alpha (Mossland)

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 meaningful behavioral traits: answers are limited to 300 characters, and it will answer honestly when the context lacks the information. This goes beyond basic read/write indication and is useful for the 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?

The description is concise and front-loaded, stating the core purpose in the first sentence followed by two key behavioral constraints. Every sentence earns its place with no wasted words.

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

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

For a simple single-parameter tool with no output schema, the description covers the input, output style (answer + citation), length limit, and context-absence behavior. It lacks detailed return structure but is reasonably complete for the tool's simplicity.

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

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

Schema coverage is 100% for the only parameter ('question'), and its description already specifies language and length constraints. The tool description adds no additional parameter-level detail, so the baseline of 3 is appropriate.

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

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

The description clearly states the tool's function: converting a natural language question into Alpha's RAG-based answer with citations. It uses a specific verb ('ask') and resource ('Alpha's data'), and the answer length limit and honesty policy distinguish it from sibling tools like search_alpha.

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 natural language questions but does not explicitly address when to use it over siblings (e.g., search_alpha) or any exclusions. It is not misleading but lacks explicit guidance on alternatives.

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

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

The description discloses the core behavioral rule (5-minute window with ≥1% price change) and the time window, which is useful. However, since no annotations are provided, the description carries full burden, but it omits side effects, authentication needs, rate limits, or output format, leaving the agent under-informed about operational 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 concise sentence that front-loads the core purpose ('active price signals within the last N hours') and appends the essential pulse definition in parentheses. Every word earns its place with no redundancy.

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

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

For a simple one-parameter tool, the description covers the core purpose and signal criteria, but omits output structure, parameter bounds, and edge cases (e.g., no signals found). Since there is no output schema or annotations, the agent may have to guess the response format, making the description only partially complete.

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

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

The schema already documents the 'hours' parameter with a description of 'query window (default 24)', but the tool description explicitly maps N to hours, clarifying that the parameter controls the lookback period. This adds semantic meaning beyond the schema's terse label, enhancing understanding.

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 identifies the tool as retrieving 'active price signals' within the last N hours, with a specific criterion of 5-minute window ≥1% change. This distinguishes it from sibling tools focused on entities, events, or topics, though it does not explicitly name alternatives.

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

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

No guidance is provided on when to use this tool versus alternatives, or any exclusions or prerequisites. The description only implies usage through its purpose, which is insufficient for an agent to decide between this and sibling tools like ask_alpha or get_macro_snapshot.

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 discloses that the connections are AI-synthesized hypotheses ('AI 합성') and indicates a sorting/limit behavior ('8개 정렬'). This goes beyond typical annotations. However, it doesn't mention output format, error cases, or side effects, and no annotations are provided to cover the rest.

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 concise (one short sentence), but the phrasing is ambiguous, especially '8개 정렬'. It's under-specified rather than efficiently clear, sacrificing clarity for brevity.

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 or annotations, the description must carry the full burden. It provides a rough idea of the return (AI-synthesized hypotheses, 8 sorted) but lacks detail about the response structure, fields, pagination, or error behavior. Given the low complexity, it barely meets minimum viability.

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

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

The schema has a single parameter 'entity_id' with no description, and the description only implies it refers to the entity in question via 'Entity의'. This adds minimal meaning; it doesn't specify the ID format, type of entities, or how it's used beyond being the source entity.

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 that the tool gets causal hypotheses between an entity and other entities, which is a specific verb+resource. It distinguishes itself from siblings like get_entity or search_alpha by focusing on connections. However, the phrase '8개 정렬' is ambiguous and not fully clear, so it's not a perfect 5.

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?

There is no guidance on when to use this tool versus alternatives. No exclusions, prerequisites, or alternative tool mentions. The description only implies it should be used to fetch connections for an entity.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It clearly describes the output composition (stance distribution, AI card, 5 videos) and the dependency on search_alpha for the ID. It doesn't mention error cases or rate limits, but for a read-only get tool, the provided info is adequate.

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

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

The description is a single dense sentence that front-loads the purpose ('Entity 상세') and then lists the three output components and the prerequisite. Every word adds value, with no redundancy or filler.

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

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

Given the tool has only one parameter, no annotations, and no output schema, the description does a good job covering what the agent needs: it explains how to get the ID, what the response includes, and the key behavioral trait of returning exactly 5 videos. It could detail the response structure further, but for a simple get tool this is sufficient.

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

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

The schema already fully describes the 'id' parameter with examples, so the baseline is 3. The description adds practical guidance on how to obtain the ID (via search_alpha), which goes beyond the schema and helps the agent correctly supply 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 clearly states the tool returns entity details including stance distribution, an AI-synthesized card, and 5 related videos. It specifies the resource (entity) and the specific verb 'detailed' (상세), distinguishing it from sibling tools like search_alpha and list_topic.

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 instructs to first find the ID via search_alpha, providing a clear usage prerequisite and pointing to a sibling tool. This implies get_entity is for retrieving details after obtaining an ID, not for discovering entities, which is a distinct usage context.

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

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

With no annotations provided, the description carries the full burden. It does disclose the return contents (summary, AI synthesis, linked entities), which is useful. However, it doesn't explicitly state that the operation is read-only or has no side effects, though 'get' implies this. It also doesn't mention any potential variability from AI synthesis.

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 phrase, front-loaded with 'Event 상세' (Event details), and immediately conveys the key content. No unnecessary words or repetition.

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 tool with no output schema, the description adequately covers what the tool returns (summary, AI synthesis, linked entities) and implies the resource type. It lacks some context like return format or any constraints, but given the low complexity, it is fairly complete.

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

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

The schema has a single 'id' with no description, and the description does not explicitly explain it. However, the tool name and type make it obvious that 'id' refers to the event identifier. The description adds minimal semantic value beyond the schema, but for a single obvious parameter, this is acceptable.

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 that the tool retrieves event details, including case summary, AI synthesis, and linked entities. The verb 'get' is implied by the name, and the resource ('Event') is explicit. It distinguishes from sibling 'list_events' by focusing on a single event.

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 is provided about when to use this tool versus alternatives. It doesn't mention that it's for retrieving a single event by ID or that 'list_events' should be used for browsing. Without such direction, the agent may not know which tool to select.

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

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

There are no annotations, so the description carries the full burden of behavioral disclosure. It only states 'current' data, implying a snapshot without providing details on data source, update frequency, caching, or response format. It does not mention whether data is real-time, delayed, or point-in-time, nor any side effects or permissions. This falls short of transparent behavioral disclosure.

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, compact sentence in Korean, front-loaded with the main idea ('current US + KR macro data') and followed by a concrete list of examples. Every word adds value, and there is no redundant or unnecessary information. It is perfectly concise for a no-parameter tool.

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 (no params, no output schema, no annotations), the description provides a fairly complete picture of the data content. It names key indicators and uses 'etc.' to indicate more. While it doesn't specify return format, the tool name and content list make the purpose clear. A bit more context about the data's temporal nature or source would improve completeness, but for a macro snapshot, it is sufficient.

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 tool has zero parameters, so there is nothing to document. The baseline of 4 applies. The description does not contradict or add param semantics, but none are needed. The agent can invoke the tool without any input, and the description outlines the output content.

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

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

The description clearly states the tool's purpose as retrieving current US and Korean macro data, listing specific indicators such as Fed Funds, BoK base rate, US 10Y, Korean 3Y, and USD/KRW. This is specific and differentiates it from siblings like get_today_brief or get_entity, which likely have broader or different scopes.

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 use case: when you need current macro data for the US and Korea. However, it provides no explicit guidance on when to prefer this tool over alternatives, such as get_today_brief, nor does it state any exclusions or recommended scenarios. The lack of explicit when-to-use advice makes it merely implied.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It adds valuable context by specifying that the brief is AI-synthesized and includes specific content sections, which goes beyond the schema. However, it does not state that this is a read-only operation, whether data is cached, or if any special permissions are needed. The disclosed content structure is positive but incomplete.

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, efficient sentence that front-loads the purpose and includes essential content details. No wasted words; it is appropriately sized for the tool's simplicity.

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

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

For a tool with one optional parameter and no output schema, the description provides sufficient information about what is returned and how the date is interpreted. It lacks explicit output schema but the content list helps. The mismatch between 'today' in the name and 'yesterday' in the description is a minor gap, but overall the description is complete enough for basic 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?

The schema already provides full coverage for the single 'date' parameter, including format (YYYY-MM-DD) and default behavior (yesterday). The description does not add additional parameter semantics beyond what is in the schema. Per the baseline rule for high schema coverage, a 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 returns a daily brief of the Korean market for a specific date, with content components (oneLine + why + 5 points + quotes). It uses an implicit 'get' verb and identifies the resource precisely. However, it does not explicitly distinguish itself from sibling tools like get_macro_snapshot, though the Korean market focus and AI synthesis are distinctive.

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. The description only states what it does (get a daily brief), leaving the agent to infer usage context from the name. There is no mention of exclusions or complementary tools, so the agent receives no decision support.

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

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

With no annotations, the description carries full behavioral burden. It discloses the main return components (description, AI synthesis, stance distribution, related videos), but does not mention side effects, permissions, or error behavior. Since it's a get_tool, read-only nature is implied but not stated.

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, compact sentence with clear structure, front-loading 'Topic 상세' and using separators to list contents. Every word adds value with no redundancy.

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

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

Given the simple 1-parameter schema and no output schema, the description does a good job of outlining the expected response content. However, it omits parameter semantics and usage conditions, leaving some gaps for an agent relying solely on the description.

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

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

The schema has one undocumented string parameter 'id' with 0% description coverage. The description does not explicitly explain that 'id' refers to a topic identifier, forcing the agent to infer it from the tool name and context. The description fails to compensate for the schema gap.

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 this tool returns detailed topic information (설명, AI 합성, stance 분포, 관련 영상), distinguishing it from siblings like list_topics and get_entity. The verb 'get' is in the name, and the description specifies the resource and scope.

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

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

Usage is implied: this is for retrieving detailed topic data. However, there is no explicit guidance on when to use this tool versus alternatives like list_topics or get_macro_snapshot, and no exclusions 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?

With no annotations, the description notes it lists 'all canonical events,' which implies a read-only operation, but it doesn't disclose any behavioral traits such as result ordering, pagination, or potential payload size. The word 'canonical' adds some context but doesn't substantially expand behavioral understanding.

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 phrase, front-loaded with the core action and resource. It contains no filler or redundant information, making it extremely concise and well-structured.

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

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

For a parameterless listing tool, the description sufficiently states scope ('all canonical events of Alpha') and is largely complete given the lack of complexity. However, it doesn't mention whether results are sorted, what fields are returned, or how it relates to get_event for per-event details, leaving 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 tool has zero parameters, so the schema description coverage is trivially 100%. The description provides no parameter-specific meaning because none exist, aligning with the baseline score of 4 for parameterless 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 lists all canonical events of Alpha, using a specific verb (목록 = list) and resource (events). This distinguishes it from get_event (singular) and other sibling tools, making the purpose unequivocal.

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?

There is no guidance on when to use this tool versus alternatives. It doesn't mention that get_event should be used for a single event or that search_alpha provides filtering, leaving the usage context entirely unaddressed.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It adds valuable context by stating the personas are synthetic characters and not 1:1 real-name imitations, preventing potential misuse. However, it does not describe other behaviors like output format or data source, so it is 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 concise sentences with no wasted words. It front-loads the primary function and adds a critical ethical note about synthetic personas in the second sentence, earning 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 list tool with no parameters, the description is mostly complete: it specifies exactly 8 personas and their synthetic nature. The lack of an output schema means the description could have hinted at the data structure (e.g., providing persona names/descriptions), but this is a minor gap.

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

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

There are zero parameters, and the schema is empty (100% coverage). Per guidelines, a baseline of 4 is appropriate when no parameters exist; the description need not document any parameter semantics.

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 this tool lists a catalog of Alpha's 8 AI personas. It uses a specific verb (list/catalog) and resource (personas), and is distinguishable from sibling tools like list_events and list_topics which target different resource types.

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 when an agent needs to enumerate Alpha's AI personas, but does not explicitly mention when to prefer this tool over alternatives, nor does it provide exclusions or prerequisites. The name and context make the purpose clear, but guidance is implicit rather than explicit.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the list is limited to 'canonical' topics, which is a behavioral filter, but it does not explain what canonical means, whether there is pagination, or any side effects. For a simple read-only list, this is adequate but not rich.

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

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

The description is a single, clear sentence that directly states the tool's function. No unnecessary words or repetition.

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 its simplicity, the description covers the core purpose, but without an output schema or mention of return format, an agent does not know what fields each topic includes. It is minimally sufficient but leaves some 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 tool has zero parameters, and the schema reflects that with 100% coverage. The description does not need to explain any parameters, aligning with the baseline score of 4 for tools without 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 tool returns a list of all canonical topics for Alpha, distinguishing it from get_topic which targets a single topic. The verb is implied by the noun '목록' but the intent is unambiguous.

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

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

The description implies this is the tool to use when you need the full set of canonical topics, but it does not explicitly state when to use it over get_topic or other list tools. No exclusions or alternatives are 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?

With no annotations, the description carries the burden of disclosing behavior. It states the search scope and language support, but does not mention pagination, filtering behavior, or return format. It is a read operation by nature, but the description adds no explicit safety or side-effect information.

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 concise sentences, front-loaded with the core purpose and supplemented by the domain scope. 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 search tool with fully documented parameters and no output schema, the description covers the essential aspects: what is searched, what keyword types are supported, and the target domains. It lacks explicit return format, but given the simplicity, it is largely complete.

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

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

Schema description coverage is 100%, so the schema already fully documents the two parameters. The description adds value by specifying the language and content domains but does not go beyond the schema for parameter meaning.

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 searches Alpha's entities, topics, events, and creators using Korean crypto/macro/politics/international keywords. The verb 'search' is specific and the resource scope is well-defined, distinguishing it from sibling tools like get_entity or list_topics.

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 keyword-based search across multiple content types, which is distinct from direct lookup tools (get_entity, get_topic) or listing tools (list_topics, list_events). It does not explicitly state when not to use it, but the context is clear enough.

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