Legend Saju

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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the scoping constraint that both birth data sets are required and relationship-focused queries are the intent, but it does not describe deeper behavior such as output structure, analysis style, or limitations. This is acceptable but not high-value beyond the 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 description is only two sentences long, front-loads the triggers, and statesthe essential prerequisite. Every sentence serves a purpose and there is no redundant repetition of the tool name or title.

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 schema is rich and the output schema exists, the description provides enough context for an agent to identify the tool and know it needs two birth data sets. It does not spell out every parameter, but the schema covers those details. It's concise but 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?

With 50% schema description coverage, the schema carries a moderate amount of parameter meaning. The description contributes 'Requires both people's birth data,' which maps helpfully to birth and partnerBirth, but it does not add meaning for question, outputMode, detailLevel, maxClaims, or targetDate. The added value over the schema is useful but incomplete.

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 a specific action and resource: analyzing two-person compatibility. It gives concrete trigger phrases (궁합, 결혼 가능성, relationship compatibility) and differentiates itself from siblings by noting 'two birth charts compared.'

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?

It explicitly says 'Use this when the user asks...' and names the exact conditions that should select this tool. It also adds a key precondition: both people's birth data are required. It does not name alternatives or explicitly say when not to use it, so it falls one point short of the strongest 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?

The description discloses an important behavioral trait: it keeps legal Hanja observations, declared stroke standards, and birth-based naming guidance separate. This adds meaningful context beyond the readOnlyHint and destructiveHint annotations, which already indicate that this is a safe, non-destructive analysis.

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 with no fluff. The first sentence tells the agent exactly when to use the tool, and the second discloses a key behavioral distinction. 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?

The tool has a complex nested schema, output modes, and many parameters, but the description does not mention those dimensions. The output schema exists and provides some structure, but the description relies heavily on the schema and does not mention how to combine name, birth, and strokes inputs or how to choose output modes.

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 description alludes to relevant inputs like 획수 and birth-based guidance, which helps infer the `name`, `birth`, and `strokes` parameters. However, it does not provide detailed semantics for the many parameters and enums, and with schema coverage at 50%, the description only partially compensates for the 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?

Title and description clearly define the task as analyzing Korean names, with an explicit list of relevant question domains (작명, 성명학, 81수, 한자, 획수, 파자). This is specific enough to distinguish it from the sibling tools like read_fortune or analyze_compatibility.

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 starts with 'Use this for...' and enumerates naming-related use cases. It gives clear positive guidance, though it does not explicitly mention when not to use it or point to a sibling alternative.

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 annotations already communicate that this is a read-only, non-destructive operation. The description adds context that the tool is for matching a question to a method rather than producing a reading, but it does not disclose behaviors such as ranking, fallback behavior, or whether all systems are searched by default. Given the readOnlyHint present, the description 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 compact, using two sentences with no filler. It front-loads the main purpose and includes an important boundary condition with the 'Do not use it for an ordinary fortune reading' clause. Every sentence contributes real selection guidance.

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 safe read-only annotations and the presence of an output schema, the core tool behavior is reasonably covered. The main gap is the lack of clarity around how the three input parameters mainly 'systems' and 'limit' should be populated, especially since the schema itself has no parameter descriptions. An agent would likely succeed but needs to infer some invocation details.

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 needs to compensate. It partially does by providing a list of possible values for systems and implying that query holds the user's specialized question. However, the limit parameter is never explained, and no specific parameter-level guidance is given other than what a reader can infer from the list.

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 action (find/select a calculation method) and a concrete resource domain: matching a user question to a traditional method such as Saju, Qimen, Feng Shui, or naming. It also distinguishes the tool from an ordinary fortune reading, which helps differentiate it from siblings like legend_saju_read_fortune or legend_saju_cast_divination.

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 gives a clear when-to-use trigger: whenever the user asks which calculation method fits a specialized question. It also provides a when-not case by saying not to use it for an ordinary fortune reading. However, it does not name the specific sibling tool to use instead, so it misses the most explicit form of routing.

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 cover read-only and non-destructive behavior, so the description only adds scoping context: it is a casting operation, not a general reading. That is useful but does not describe internal behavior such as calculation assumptions, resolver behavior, or output side effects, though output schema likely covers some of this.

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, both directly informative, front-loaded with what the tool does and quickly followed by the key exclusion. There is no filler, repetition, or extraneous detail.

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 a rich input schema, annotations, and an existing output schema, the description covers the core decision boundary: when to use it and when to avoid. Important contextual items like the need for exact time handling and the difference from general natal readings are either in the description or captured in schema descriptions.

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 description need not repeat field meanings. It does add the high-level semantic linkage 'question time or six line values', which corresponds to questionDateTime and lineValues, but it does not provide any detail beyond what the schema already documents.

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 names the specific resource (traditional divination chart) and enumerates the exact methods it serves: 기문둔갑, 대육임, 주역, 점괴. It also clarifies that this is for concrete decision casts from a question time or six line values, distinguishing it from generic fortune 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?

The description gives explicit when-to-use conditions, including the concrete methods and required input types, and clearly states what it should not be used for. It does not explicitly name the alternative tool for general natal readings, but the sibling list makes the intended alternative evident.

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 and destructiveHint, and the description adds meaningful behavioral detail: it only handles five audited concepts, returns both consensus and conflicting motifs, and does not fabricate interpretations from the rest of the corpus. This gives agents accurate expectations beyond the structured 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 description is two sentences with no filler: the first front-loads the main use and scope, and the second quickly states its output and limitation. Every clause adds useful information, and the phrasing is compact for a 7-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 output schema, annotations, and high parameter coverage, the description does not need to explain return values in detail. It adequately covers scope, output content, and a critical behavioral limitation. It could be slightly stronger about when to choose alternatives, but nothing essential is missing for calling the tool correctly.

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

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

Schema description coverage is 86%, so the input schema already documents most parameters in detail. The description does not add substantial semantic nuance to parameters, but it reinforces the core purpose of the 'dream' parameter by emphasizing faithful dream interpretation. This is adequate given the high schema coverage.

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 names a specific verb and resource: interpreting dreams (해몽, 꿈풀이), and clearly separates this from the sibling divination tools. It also specifies the exact scope: only five cross-culturally audited concepts, returning shared motifs and conflicting conditions with excerpts.

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 directs use for dream interpretation and imposes an important boundary: it does not produce invented meanings from the remaining raw corpus. It does not name sibling alternatives or say when to use them, but the limitation gives useful 'when not to rely on this' 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?

Annotations already identify it as read-only and non-destructive; the description adds meaningful behavioral content by calling out 'no model or network call' and 'deterministic.' This goes beyond the annotations and clarifies that invoking the tool will not trigger side effects. No contradiction with annotations is present.

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 short sentences carry all the essential information. The core action is front-loaded, and each added phrase — 'live,' 'source-traceable,' 'deterministic,' 'no model or network call' — contributes meaning. There is no fluff 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?

The tool is a simple zero-parameter introspection with an output schema already provided. The description covers the important behavioral context: what the response is and that nothing is executed via model or network. No further information is needed for an agent to correctly invoke it.

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 an empty input schema, so the description has no parameters to explain. The baseline for zero-param tools is 4, and the description's 'No model or network call' also helps avoid invocation confusion.

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 gives a specific verb and object — 'Return the live, source-traceable deterministic engine manifest' — and adds 'No model or network call,' which is unambiguous and distinguishes this from the model-using divination siblings. The title 'Inspect Legend Saju' reinforces the read-only intent. An agent can tell what this tool does without opening the schema.

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 does not explicitly name sibling alternatives or state when not to use it. However, 'No model or network call' implies a lightweight, deterministic inspection path, which gives some contextual guidance. It stops short of explicit `when to use this` vs. `when to use a sibling`, so the inference value is moderate.

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 show readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the call is clearly a safe read operation. The description adds no further behavioral context such as state changes, external effects, or limits. There is no contradiction with the 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?

Two sentences contain no filler. The first sentence captures the full functional scope, and the second succinctly names the two key controls for varying the tool's behavior. All content is front-loaded.

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

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

The description covers the tool's core purpose and two major controls well, but it omits context needed for richer invocations: which parameters correspond to 'annual' reading, when to supply targetDate, or budget-limited output. The schema and output schema cover part of this, but the description alone has noticeable 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 description calls out detailLevel and outputMode, mapping them to calculation breadth and response projection, which reinforces the schema. However, it does not add meaning beyond what the schema already says, and important parameters like targetDate, asOfYear, and maxClaims are left unaddressed.

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

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

The description uses a specific verb ('read a Saju fortune') plus an explicit list of reading domains: natal, current, annual, career, wealth, relationship, health, and action. This distinguishes it from sibling tools like compatibility, name, dream, or divination without needing to open their schemas.

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?

It says 'Use this for' and enumerates available reading categories, giving clear when-to-use context. It doesn't explicitly name which siblings to avoid, but the domain list is enough to route an agent to this tool instead of compatibility, dream, or divination 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 annotations already declare readOnlyHint=true and destructiveHint=false, so no contradiction exists. The description adds genuinely useful behavioral context beyond annotations: it is a planning/dispatch tool that can take specific capability IDs or auto-plan from the user's question.

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 dense but front-loaded with the core use case, then gives method coverage, then operational routing guidance, then a direction to focused tools. The long method list is the tool's main purpose and is relevant; no sentence is wasted.

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 high complexity, the description makes the critical selection and invocation decisions clear. The output schema exists and does not need to explain return values. Additional examples or a per-parameter walkthrough would help but are not strictly needed for a selector-type 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 only 45%, so the description has to compensate for missing parameter context. It directly clarifies the two most important semantic choices: `requestedCapabilities` can hold discovered method IDs, and the `question` field can trigger server-side routing. It does not describe every parameter, but covers the key orchestration mechanism.

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 immediately identifies the tool as the correct choice for 'expert, mixed-system, or named-method requests' and enumerates a concrete list of traditional methods. It clearly distinguishes itself from focused sibling tools by saying 'Use focused tools for ordinary single-goal requests.'

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?

It explicitly states when to use this tool (expert, mixed-system, named-method requests) and when not to use it (ordinary single-goal requests). It also tells the agent exactly how to invoke it: pass discovered capability IDs in `requestedCapabilities` or let the server plan from the question.

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 notations already disclose behavior with hints, and the description does not need to restate basic properties. The description provides a usage boundary, but it does not reveal internal behavior, such as the output is generated, how constraints affect date results, or whether any cost/resource limit setting exists.

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 front-load the exact trigger condition and include a clear negative exclusion. There is no fluff, and every phrase carries operational meaning.

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 the output schema and schema modes, the description is enough for route selection, especially the explicit anti-fortun miss-use case. It leaves the intended content of `question` and the practical semantics of `rangeDays` to the schema, which is acceptable but not fully comprehensive.

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 description is syntax and the schema itself, together with intended behavior or additional keyword types. Schema coverage is 63%, with moderate descriptions, but the valid text does not add anything beyond the schema for the 4 and nested 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 descriptions states a specific verb, selection function, and an explicit resource: faum, 좋음. 날2, 계약일, 이사일, 개업일, 수술일, and another date-selection task. It also differs from sibling-forline `fortune` requests, which clarifies the boundary and contrasts with tools like read_fortune.

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 gives explicit trigger, condition, and a of tasks (`택일`, `좋성 12시`, etc.) and says not to use when a fortune request merely mentions the year. what more positive thanks.

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