yarrow

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does a good job by specifying the line-value encoding (6,7,8,9), the bottom-to-top order, the condition for a changing hexagram, and the determinism effect of seed. It stops short of describing error cases or the exact JSON response shape, but the core runtime behavior is transparent enough.

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 sentence leads with the action and the key outputs; the second sentence adds an optional-parameter nuance. Every clause earns its place, and the structure is front-loaded for an agent to quickly understand purpose.

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

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

Given three optional parameters and no output schema, the description covers the essential return semantics (primary hexagram, line values, moving lines, changing hexagram) and an important behavioral knob (seed). It could be slightly more complete by mentioning how the result is structured or how 'method' affects probabilities, but those details are already in the schema, so this is sufficiently complete for casting a hexagram.

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?

All three parameters are fully described in the input schema (100% coverage), so the baseline is 3. The description adds extra value for the seed parameter by explaining its purpose ('deterministic... useful for testing or reproducing a reading'), which goes beyond the schema's terse 'Optional seed for deterministic casting.' The method and question parameters are already well covered by the schema, so no additional description is necessary.

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 opens with 'Cast a hexagram for an I-Ching consultation,' which is a specific verb+resource pairing that clearly distinguishes this tool from the lookup siblings (lookup_hexagram, lookup_yilin). It also enumerates the returned artifacts (primary hexagram, lines, moving lines, changing hexagram), making the tool's function unmistakable.

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 context is implied: the tool is for I-Ching consultations, and the seed parameter is explicitly positioned for testing/reproducing readings. However, it never contrasts itself with the sibling tools (e.g., 'use lookup_hexagram to inspect a known hexagram' or 'use divine for a broader reading'), so the when-to-use vs alternatives guidance remains 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?

With no annotations, the description carries the burden. It discloses determinism via seed, the upright orientation, and the source text excerpt. However, it does not explain behavior when seed is omitted (e.g., random draw) or any other side effects, leaving some ambiguity.

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-loaded with the core action, and every word earns its place. 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 simple with two optional parameters. The description covers the draw type, determinism, and return value (source excerpt). Not needing to explain output schema, it is sufficiently complete for a tool of this 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%, and the schema already describes both parameters clearly. The description repeats the seed's purpose but adds no new meaning beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states the tool draws one upright Major Arcana card for reflection, which differentiates it from siblings like cast_hexagram (hexagram) and lookup tools. The verb 'draw' and resource 'Major Arcana card' are specific.

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 indicates when to use it (for tarot reflection) but provides no guidance on alternatives or when not to use it. Sibling tools exist but no exclusions or comparisons are made.

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 full responsibility for behavioral disclosure. It goes beyond typical descriptions by detailing output order ('show the classical sources first, then offer a thoughtful reflection'), philosophical stance ('Reflection, not prediction'), language support, and quota policy including what does NOT consume quota (timeout, provider failure, incomplete response, cancellation). This is exceptionally 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 relatively long but information-dense, with each sentence contributing value. It is front-loaded with purpose ('Ask the I Ching. See your next step.'), then covers behavior, name stability, languages, and quota. The sentence about the divine name being stable for client compatibility is somewhat extraneous for an agent, but not excessively verbose.

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 absence of an output schema, the description adequately outlines what the tool does and what to expect: a hexagram cast, classical sources, and a reflection. It also covers edge-related behavior (quota). It could be more explicit about the exact structure of the response (e.g., whether it includes lines, translations), but it is sufficiently complete for an agent to understand the tool's function.

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 60% (seed, question, device_id have descriptions in schema). The description adds context for locale by listing supported languages and clarifies device_id's role in quota tracking. However, it adds no direct meaning for the 'seed' and 'method' parameters beyond what the schema already states or implies (e.g., enum values).

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: 'Ask the I Ching. See your next step. Cast a hexagram, show the classical sources first, then offer a thoughtful reflection grounded in those sources.' It uses specific verbs (ask, cast, show, offer) and resource (I Ching), and distinguishes from siblings by emphasizing the reflective reading rather than just casting or lookup. The phrase 'Sources first. Reflection, not prediction.' further clarifies the purpose.

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 clear context for when to use this tool: when you want an I Ching reading with classical sources and reflection. It does not explicitly mention alternatives or exclusions relative to sibling tools (cast_hexagram, lookup_hexagram, lookup_yilin), but the use case is well implied. The quota information also gives practical usage 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?

No annotations are provided, so the description carries the burden. It discloses the detailed contents of the response (judgment, image, Tuan commentary, etc.) and notes 'available' source material, indicating conditional presence. It does not mention error handling, but for a read-only lookup, this is reasonably 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 a single, front-loaded sentence that starts with the action and resource. It lists many components in a structured way, making it dense but efficient. It could be slightly more concise by trimming the list, but it is not overly verbose.

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 no output schema, the description provides a thorough list of return fields and mentions language coverage, giving a clear sense of what to expect. It does not detail behavior around the compact parameter, but the schema covers that. Overall, it is sufficiently complete for a lookup 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 descriptions cover 67% of parameters (number and compact), while locale lacks a description. The description hints at language options via 'Chinese and English source material' but does not explicitly explain the locale parameter. It adds some context beyond the schema but does not fully compensate for the uncovered 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 the full classical sources for a hexagram by number, enumerating specific components like judgment, image, and commentaries. This distinguishes it from sibling tools like cast_hexagram and divine, which involve casting or 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 implies usage for looking up a hexagram's classical material by number, but it does not explicitly state when to use this tool versus alternatives like lookup_yilin or cast_hexagram. No exclusions or alternative guidance is provided, leaving the context somewhat 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 disclosing behavior. It usefully reveals this is a deterministic local lookup, not generative AI. However, it doesn't describe the output format, whether verses are in Chinese or translated, or what happens for invalid hexagram combinations, so transparency is partial.

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—two sentences—with the core action front-loaded. Every phrase earns its place, and there is no redundant 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?

For a simple lookup tool with two integer parameters and no output schema, the description adequately covers the purpose and nature of the tool (local source vs AI). It could mention return format or error handling, but these are not critical for a minimal understanding.

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 already fully describes both parameters with ranges and meaning (1-64). The description adds the relationship between primary and changing hexagrams, but this is marginal since the schema covers each parameter's semantics. Baseline of 3 applies due to 100% 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 clearly states the tool's function: look up a 焦氏易林 verse for a primary hexagram changing into another. It uses a specific verb ('look up') and resource, and distinguishes itself from sibling tools by clarifying it's a local classical-source lookup, not an AI 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 provides context on when to use this tool by noting it's a local classical-source lookup rather than an AI reading, implying it's for retrieving exact verse text. However, it doesn't explicitly name alternatives or state conditions like 'use this when you need a literal verse rather than interpretation.'

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 takes on full responsibility for behavioral disclosure. It details the output structure (calibrated answer first, then five sections), explicitly disclaims guaranteed predictions and mutual-confirmation, and mentions quota sharing ('daily quota is shared with completed divine readings'). This goes beyond minimal transparency, though it does not address potential side effects like determinism or result variation.

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, front-loaded with the core purpose, followed by output structure and constraints. Every sentence earns its place; there is no redundancy or fluff. The description is compact yet rich in information.

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

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

Given the tool's complexity (combined divination, 6 parameters, no output schema), the description provides a clear picture of the return format, philosophical stance, and quota limit. It lacks explicit details on error handling or exact parameter behavior, but the overall context is sufficient for an agent to set expectations. A minor gap is not specifying how the two traditions are combined or calibrated.

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 67%, leaving locale and method without descriptions (only enums). The description does not explain these parameters or the seed/device_id parameters. It only adds context around 'question' (calling it 'real question'), which is already described in the schema. The description fails to compensate for the missing 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 uses a specific verb ('bring') with explicit resources ('I-Ching cast' and 'upright Waite-Smith Major Arcana card') and a clear output structure ('five grounded sections'). It distinguishes itself from sibling tools by explicitly combining two traditions, unlike cast_hexagram or cast_tarot which focus on one.

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 when to use this tool: when the user wants both an I-Ching cast and a Tarot card for the same real question, phrased as 'bring one real question to two independent symbolic traditions.' It does not explicitly name alternatives or state when not to use it, but the context is clear enough for an agent to infer the intended use case.

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