AstroWay Divination and esoterica

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint. Description adds that it returns a 'plain-text human-readable summary' and clarifies the budget-checking purpose, providing useful context beyond annotations.

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

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

Three efficient sentences: purpose, usage guidance, and return format. Front-loaded with key information, 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?

Despite lacking an output schema, the description specifies the return format (plain-text human-readable summary). For a simple status check tool, this is complete and 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?

Tool has zero parameters, so schema coverage is 100%. Description does not need to explain parameters, and it adds value by hinting at the output format.

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 the verb 'Check' and the resource 'API key status' with specific attributes (tier, credit balance, rate limits, monthly cycle reset). It distinguishes itself from the many sibling astrology calculation tools.

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 instructs to run this tool BEFORE invoking expensive endpoints, providing credit thresholds (Tier 4+ at 100+ credits, Tier 6/7 at 500-5000 credits) to confirm budget.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered structurally. The description adds the useful guarantee that the emitted schema is the schema the endpoint validates and that the objects carry no vendor-specific fields, but says nothing about cost, rate limits, or response size behavior beyond what the schema states.

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 visible portion is front-loaded on what is returned and the two format shapes, with no filler. It is somewhat terse for a tool with six parameters and a listed default/select semantics, but every visible sentence carries information.

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

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

With an output schema present, the description need not explain return values, and annotations cover the read-only/idempotent profile. The remaining gap is routing: nothing tells the agent when to choose this over astroway_mcp_tools_list or similar listing tools.

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 every one of the six parameters is already documented in the schema, including the format enum and the select/fields/precision semantics. The description restates the format option rather than adding new meaning, so the baseline 3 for full schema coverage applies.

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 and resource: returning agent tool definitions generated from the live OpenAPI document, in either OpenAI or Anthropic shape. That is clear enough to differentiate it from report/chart tools in the namespace, but it never names the closest sibling (astroway_mcp_tools_list) or explains the distinction, so it falls short of a 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 explicit when-to-use guidance and no stated alternative. The mention of `format=openai` as the default is parameter behavior, not a usage rule, and the agent is left to infer whether this is for building an agent, curated retrieval, or an MCP tool listing.

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 readOnly/idempotent/non-destructive/closed-world, so the safety bar is low; the description still adds real value by clarifying that endpoints are NOT invoked and that results are cached with a 5-minute TTL. It also discloses the return shape (total + per-endpoint breakdown with tier annotations), which is meaningful since no output schema 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?

Three tight sentences, front-loaded with the core capability and the non-invocation guarantee, followed by workflow guidance and the cache note. Nothing 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?

Despite having no output schema, the description explains the return value, and the invocation-free and cache behaviors are covered. For a one-parameter, read-only estimator this is fully 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?

Schema description coverage is 100% and the single 'endpoints' parameter is fully documented with examples and the leading-slash rule in the schema. The description only restates 'one or more endpoints' without adding format or constraint detail beyond the schema, so baseline 3 applies.

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?

States a specific verb and resource ('Estimate the credit cost of one or more endpoints') and immediately pins the scope with 'WITHOUT invoking them', which no sibling tool does. An agent can distinguish this from the many invocation/report siblings at a glance.

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?

Gives explicit workflow guidance: 'estimate first, ask user confirmation, then invoke' for multi-step planning. This is clear when-to-use context, though it names no alternative tool or when-not-to-use condition.

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

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds content-type detail and the cost line (5 credits, Tier ½), which is genuine behavioral context, but says nothing about response size for a 'full catalogue' or pagination/limits.

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 content statement is a single front-loaded sentence, with group and cost tags kept clearly separate. Nothing is padded, though 'with short and full meanings, themes' is a slightly loose enumeration.

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 an output schema present, return-value explanation is unnecessary, and the description tells the agent what the catalogue contains. However, for a bulk-catalogue tool it omits any hint about result volume or the practical benefit of the compact-mode parameters, leaving a real 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?

Schema description coverage is 100% and the description is silent on both parameters, so the baseline of 3 applies. It does not compensate for the fact that the `fields` example ('planets.name, houses.cusp') appears copied from a chart tool and is misleading for an angel-number catalogue.

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 concrete resource — a full angel number catalogue — and enumerates the pattern classes it covers (singles, masters, repeating, mirror, sequential) plus the payload (short/full meanings, themes). The word 'Full' hints it is the whole-corpus variant rather than a lookup, but no sibling is named, so the distinction from astroway_esoteric_angel_numbers_number or _decode must be inferred.

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 when-to-use or when-not-to-use statement and no reference to the obvious alternatives (astroway_esoteric_angel_numbers_number for a single number, _today for a daily draw, _decode for interpreting an observed number). The agent is left to guess that this is the bulk retrieval tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description. The description's only added behavioral signal is the cost note (plan-dependent, not in the public credit manifest), which is genuinely useful but thin. No return-shape detail is needed since an output schema 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 compact sentences with the core purpose front-loaded, followed by clearly demarcated metadata lines for group and cost. Efficient, with no redundancy in the prose itself.

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 low-complexity single-lookup endpoint with one required parameter, full schema coverage, an output schema, and read-only/idempotent annotations, the definition supplies enough to invoke correctly. The missing piece is routing guidance among the crowded angel-number sibling set, which is a usage gap rather than a completeness failure.

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 all three parameters (n, fields, precision) are already documented in the schema. The description restates the life-path domain from the schema and adds nothing about `fields` or `precision` (compact-mode round-tripping), so this is the baseline 3.

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 resource (angel numbers) and the axis that selects it (aligned to a given life-path number), and repeats the valid input domain. It is distinguishable from siblings by that parameter axis, though it never names an adjacent tool like angel_numbers_number or angel_numbers_today to sharpen the distinction.

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?

"Useful to identify recurring numerical signatures aligned with one's soul path" is a benefit statement rather than when-to-use guidance. No conditions, exclusions, or alternative tools are named, so the agent must infer when this beats the other four angel-number endpoints.

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 the full safety profile (readOnlyHint, idempotentHint, non-destructive, closed-world), so the description need not restate it. It does add cost/pricing context ('10 credits (Tier 1)') and a rough sense of the return payload, but since an output schema exists, the return summary is largely redundant and no error, rate-limit, or credit-consumption-on-failure behavior is disclosed.

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 front-loaded sentences followed by compact Group/Cost tags; every element earns its place with no filler. The pricing tag is arguably metadata rather than description, which keeps it just under a 5.

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 an output schema covering return values and annotations covering safety, the main remaining gaps are sibling disambiguation and semantics for the undocumented 'context'/'sequence' parameters. Adequate for a simple read-only decode tool, but not fully self-contained.

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 50%: 'fields' and 'precision' are documented in the schema, while 'context' and 'sequence' are not. The description partially compensates by indicating that the sequence is numeric and that context is an optional 'life context', but it adds no format, length, or usage detail beyond that.

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?

States a specific verb+resource (decode a numeric sequence) and even summarizes the output (pattern classification, exact match, reduced single-digit meaning), so the agent knows what the call produces. It does not differentiate from close siblings such as astroway_esoteric_angel_numbers_number or astroway_esoteric_angel_numbers_today, so it stops short of a 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?

No explicit when-to-use statement, no prerequisites, and no mention of the alternative angel-number siblings. The phrase 'in optional life context' hints at the context parameter but gives no guidance on choosing this tool over the other angel-number endpoints.

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 readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds genuinely non-redundant behavior: unindexed numbers fall back to a pattern classification plus reduced single digit. The cost note is vague ('see your plan') and adds little.

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 front-loaded sentences with no wasted prose; the fallback behavior comes second where it belongs. The bracketed cost line is a placeholder that neither helps selection nor informs invocation.

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?

An output schema exists, so return values need not be described, and annotations cover the safety profile. Purpose plus the fallback rule fully equip the agent to invoke this three-parameter, single-required lookup 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?

With schema description coverage at 100%, the schema fully documents `number`, `fields`, and `precision`, so the baseline is 3. The description only restates that the input is a specific sequence and echoes the fallback already stated in the `number` schema description, adding no new syntax or format detail.

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 and resource ('look up the meaning of a specific angel number sequence'), which makes the number-oriented lookup distinguishable from numberless siblings in principle. However, it never names the confusingly similar siblings (astroway_esoteric_angel_numbers, _decode, _by_life_path_n) to make the distinction explicit.

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 only implied by the fact that it consumes a 'specific angel number sequence,' and the fallback sentence tells the agent unindexed numbers are still handled. There is no explicit routing guidance toward alternative angel-number tools like _decode or _today, so the agent must infer the choice.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds the deterministic digit-sum reduction method, which is useful, but says nothing about the credit cost, output shape, or what happens for an invalid date.

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 tight sentences, front-loaded with the core purpose, plus a compact group/cost footer. It would be a 5 if the phantom date parameter were removed rather than being the sole usage sentence.

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?

An output schema exists so return values needn't be described, and annotations cover safety, so the remaining burden is light. Still, the description neither differentiates from siblings nor reconciles its date-query claim with the schema, leaving a gap for a low-complexity but crowded tool family.

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% for the two real parameters (fields, precision), so the schema does the heavy lifting. The description instead advertises an optional `?date=YYYY-MM-DD` query parameter that does not exist anywhere in the input schema, which actively misleads rather than adds 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?

States a specific verb and resource ('Compute today's personal angel number from date') plus the algorithm (digit-sum reduced to single digit), which is more informative than the title alone. However, it never distinguishes itself from siblings like astroway_esoteric_angel_numbers, _number, _decode, or _by_life_path_n, leaving the agent to infer that 'today' is the differentiator.

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 only usage hint is 'Optional ?date=YYYY-MM-DD query', with no statement of when to pick this tool over the other four angel-number siblings. There is also no note that omitting the date defaults to today, which is the whole point of the tool.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is fully covered without the description. The description adds that this is a static reference/taxonomy lookup and discloses a 5-credit cost, which is genuine but modest added context; no behavior beyond that (result volume, pagination of the directory) is described.

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 lead with the resource and its tag set, followed by the taxonomy note, and the group/cost metadata is compact. Nothing is padded, though the tag enumeration is a bare list rather than a tightening of 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?

An output schema exists, so return-value detail is not required, and for a read-only static directory the description plus schema and annotations are nearly sufficient. The one real gap is that a reader cannot tell from this text alone why they would pick it over the by_chakra/by_zodiac/by_purpose variants.

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 both 'fields' and 'precision' are documented in the schema and the baseline is 3. The description adds nothing about the compact-mode projection or decimal rounding, and notably the schema's example paths (planets.longitude, houses.cusp) are unrelated to the crystal domain the description enumerates.

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?

States a concrete resource with its tag dimensions ('Reference list of crystals with chakra, zodiac, planet, element, hardness, and purpose tags'), so an agent knows exactly what it gets. It does not, however, name or distinguish itself from the filtered siblings (crystals_by_chakra_chakra, crystals_by_zodiac_sign, crystals_recommend) that cover overlapping ground.

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 explicit when-to-use or when-not statement, and no sibling is named as an alternative despite four closely related crystal tools existing. The clause 'Returns chakra and purpose taxonomies for filtering' only implies that this is the discovery step before the by_chakra/by_purpose tools, leaving the routing to inference.

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 readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds only the cost caveat (endpoint not in the public credit manifest), which is genuinely useful context, but says nothing about response shape or rate/auth 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 functional sentence is front-loaded and wastes no words; the chakra list is set off in parentheses. The bracketed [Group]/[Cost] boilerplate is administrative rather than descriptive but costs little.

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?

An output schema exists and annotations cover the safety profile, so little more is required. However, the description never disambiguates the required chakra value format against its own capitalized enumeration, nor gives any usage context for a tool with three sibling 'crystals' variants.

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 has no enum for chakra ('Chakra name, lowercase.'), so the description's list of the seven chakra values is valuable information the schema omits. Minor friction: listed values are capitalized ('Root') while the schema demands lowercase, leaving exact-string format slightly ambiguous.

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?

States a specific verb+resource (crystals indexed) and the dimension (a given chakra), which implicitly separates it from the by_purpose and by_zodiac_sign siblings. It stops short of explicitly naming those siblings, so an agent must infer the distinction.

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 when-to-use, when-not-to-use, or alternative routing is given. The description only enumerates the chakra values; it never explains when this tool is preferable to astroway_esoteric_crystals_by_purpose_purpose or astroway_esoteric_crystals_recommend.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed (non-open-world) result set, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the substring match semantics ("protect" finds "protection") and a cost notice that the endpoint is not in the public credit manifest. It does not, however, describe result volume or pagination behavior, so it remains a moderate rather than rich 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?

Two short, front-loaded sentences: core behavior first, matching detail second. The bracketed Group/Cost metadata is boilerplate but carries an actionable cost caveat. No wasted prose.

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?

An output schema exists, so return values need not be explained, and annotations carry the safety profile. For a single-required-keyword lookup tool with full schema coverage, the description supplies everything an agent needs to call it correctly, including the matching rule and a cost pointer.

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 documents purpose, fields and precision, making 3 the baseline. The description reinforces the substring-match semantics of purpose (a subtle detail worth restating), but adds nothing about the fields/precision compact-mode 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 names a specific verb+resource combination (crystals indexed by purpose/intent keyword) and lists concrete example keywords, so the agent knows exactly what comes back. The name and text imply the distinction from sibling lookups like crystals_by_chakra and crystals_by_zodiac, but the description never names those alternatives explicitly, so it stops short of a 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?

Usage is implied: reach for this tool when you have an intent keyword such as love or prosperity. However, there is no statement of when to prefer it over astroway_esoteric_crystals_recommend or the chakra/zodiac variants, and no exclusions or prerequisites. Adequate but with clear routing gaps.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds two useful behavioral facts: input is case-insensitive English, and cost is plan-dependent and not in the public credit manifest — the latter is genuinely valuable for 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?

Very short and front-loaded: the core purpose is in the first clause, followed by compact group/cost metadata. No wasted prose, though the bracketed cost line is boilerplate shared across the family.

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?

An output schema exists, so return values needn't be explained, and annotations carry the safety profile, so the description is adequate on those fronts. What is missing is routing information among the numerous crystal siblings, which matters given the crowded toolset.

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 sign, fields and precision are already documented. The description's note that the sign is a case-insensitive English name adds only marginal clarification (and slightly softens the schema's 'lowercase English name' wording). Baseline 3 applies.

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?

States a specific resource (crystals) and filter (zodiac sign), which distinguishes it from siblings like crystals_by_chakra and crystals_by_purpose. However, it never names those alternatives, so the agent must infer the distinction from the tool name alone.

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 explicit when-to-use guidance, no prerequisites, and no mention of the sibling crystal-lookup tools (astroway_esoteric_crystals, by_chakra, by_purpose, recommend) that an agent would need to choose between. Usage is only implied by the phrase 'indexed for a given zodiac sign'.

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 readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely new context: a 10-credit Tier 1 cost and that results are top-N scored matches, neither of which appears in the structured fields.

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 tight sentences: purpose first, return shape second, with cost/group metadata clearly segregated. Front-loaded and no wasted prose.

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?

An output schema exists, so return values needn't be detailed, and cost is disclosed. However, for a 7-parameter tool with 29% schema coverage and no usage routing, the description leaves the compact-mode parameters and the choice among crystal siblings unexplained.

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 29% (7 params, only fields and precision documented), so the description must compensate. It clarifies that sunSign/moonSign/ascendantSign are natal sign placements and intent is keyword-based, and 'top-N' implies limit, but it says nothing about compact mode (fields/precision) or valid sign formats.

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?

States a specific verb (recommend) and resource (crystals) plus the scoring basis: natal Sun/Moon/Asc placements and intent keywords. This distinguishes it functionally from siblings like crystals_by_chakra and crystals_by_zodiac_sign, though it never names them explicitly.

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 when-to-use or when-not-to-use guidance, and no routing to the four sibling crystal tools. The agent must infer from the description that this is the multi-factor recommendation variant versus the single-filter 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds useful context beyond that: a 12-month sunset date tied to the /v1 stability policy, a 10-credit cost tier, and a data-quality caveat (RED, oral tradition, no canonical reference).

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?

Deprecation is stated three times (title, opening sentence, trailing footer), which is redundant and displaces the actual purpose sentence to the end. The content is not bloated, but the structure is repetitive rather than front-loaded with the operative 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?

An output schema exists, so return values need no explanation, and the deprecation lifecycle is thoroughly disclosed. Gaps remain around what Djamaspa actually computes and when, if ever, an agent should still call it, leaving the definition only minimally 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?

Schema description coverage is only 67% and the description contributes no parameter meaning whatsoever, adding nothing about date, fields, or precision beyond the schema. With partial coverage, the description fails to compensate for the undocumented 'date' parameter, so it does not reach the baseline 3.

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 core sentence is 'Calculate Djamaspa planetary positions for date,' which supplies a verb and resource, but 'Djamaspa' is undefined jargon with no indication of what these positions represent, leaving the purpose only semi-clear. The purpose statement is also buried beneath three separate deprecation notices rather than front-loaded.

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 effectively signals when NOT to use the tool ('Avoid using,' 'Migrate to broader /reference endpoints or remove the dependency'), which is genuine usage guidance. However, it does not name a concrete alternative tool or explain a scenario in which this tool is still the correct choice before the sunset.

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 this a safe, idempotent, closed-world read, so the safety burden is covered. The description adds only the returned content fields plus the cost metadata (5 credits); it says nothing about how large the dictionary response is or how 'fields'/'precision' compaction interacts with 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?

Two short sentences with the resource and its contents front-loaded, followed by compact group/cost metadata. Nothing is wasted, though the bracketed metadata is boilerplate rather than descriptive.

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?

An output schema exists, so return values need not be explained, and the annotations cover the safety profile. The remaining gap is routing: for a tool surrounded by four closely related dream siblings, the description does not supply the selection criteria an agent needs.

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 both parameters (fields, precision) are fully documented in the schema itself. The description adds no syntax, defaults, or examples beyond what the schema provides, making the baseline 3 correct.

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?

States the resource clearly ('dream symbol dictionary') and enumerates its contents (category, element, archetype, common/shadow meanings, recurring-dream readings), which tells an agent what it gets back. The word 'Full' hints at a distinction from the filtered siblings, but it never names them, so differentiation is left to inference.

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 when-to-use guidance at all. Siblings like astroway_esoteric_dreams_symbol_keyword, astroway_esoteric_dreams_decode, astroway_esoteric_dreams_by_element_element and astroway_esoteric_dreams_recurring_themes clearly overlap, yet the description offers no rule for choosing this one over them.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description's one addition is the cost note ('see your plan — endpoint not in the public credit manifest'), which usefully warns that pricing is opaque but stops short of stating the actual credit cost.

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?

One tight sentence that front-loads the resource and the indexing dimension, with the element list inline. The trailing bracketed Group/Cost tags are boilerplate but small; nothing is padded.

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?

An output schema exists so return values need no explanation, params are fully covered, and annotations carry the safety profile. What is missing is minor: result volume, ordering, or whether an element group can be empty.

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 `element`, `fields` and `precision` are fully documented in the schema itself; the description only restates the enum values already present there. Baseline 3 applies since the schema does the heavy lifting and the description adds no new syntax or 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?

States a concrete resource (dream symbols) and the indexing dimension (element), enumerating the five valid groupings. It implicitly distinguishes itself from keyword-based siblings like astroway_esoteric_dreams_symbol_keyword, but never names or contrasts them explicitly.

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 only implied by 'indexed by element' — an agent can infer this is a browsable lookup rather than a decode or search call. There is no statement of when to prefer this over astroway_esoteric_dreams_decode or astroway_esoteric_dreams_symbol_keyword, and no 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?

The annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds useful behavioral context beyond them: it discloses the credit cost (10 credits, Tier 1) and clarifies that returned symbols carry recurring or single-event meanings. This is a meaningful supplement even though safety behavior is already covered.

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 compact sentences front-load the purpose and return behavior, followed by group and cost metadata. Every element is useful and there is no 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?

With an output schema and full read-only annotations, the description need not explain return structure. However, for a 4-parameter tool sitting among many similar dream siblings, it omits usage guidance, does not fully document the text and recurring parameters, and does not help the agent choose between related tools.

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 50%: fields and precision are documented, while text and recurring are not. The description partially compensates by implying that 'text' is a dream narrative and that 'recurring or single-event' relates to the recurring flag, but it does not explain the text length limits or clarify whether recurring filters the output.

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 ('Scan') and resource ('dream narrative text for known symbols'), and notes the output is matched symbols with meanings. It is clear and distinct from the general 'dreams' sibling, but it does not explicitly differentiate itself from near-siblings like dreams_symbol_keyword or dreams_recurring_themes.

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 says what the tool does but gives no when-to-use guidance, no prerequisites, and no alternatives. With many dream-related siblings, the agent receives no routing help beyond the implicit purpose.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds useful cost metadata (5 credits, Tier ½), which helps budget decisions, but says nothing about return scope or behaviour beyond what annotations and the output schema carry.

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

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

A single tight sentence front-loads the resource and its examples, with cost/group metadata in clearly separated brackets. No wasted prose.

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 output schema removes the need to describe return values, and annotations cover safety, so the description is adequate for a simple lookup tool. It still omits any sibling differentiation or usage context, which is the main remaining 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?

Schema description coverage is 100%, and both optional parameters (fields, precision) are fully documented in the schema itself. The description adds no parameter meaning, so the baseline 3 applies.

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?

States a specific resource — a catalogue of recurring dream themes — and even enumerates concrete examples (falling, being chased), so the agent knows exactly what content it returns. However, it does not distinguish itself from siblings like astroway_esoteric_dreams or astroway_esoteric_dreams_symbol_keyword, so an agent cannot tell which dream endpoint to pick.

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 when-to-use or when-not-to-use guidance, and no alternative is named despite four closely related dream tools in the sibling list. The agent must infer selection from the name alone.

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 the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds two things beyond them: the exact-then-substring matching strategy, which affects how loosely a keyword can be specified, and a cost caveat that billing for this endpoint is not in the public credit manifest. It does not mention result-count limits or truncation 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?

Two tight sentences with the core action front-loaded, followed by bracketed group/cost metadata. Every line carries information; the cost caveat is worth its space, though the group tag is boilerplate.

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?

An output schema exists, so return-value explanation is unnecessary, and annotations carry the safety profile. Combined with full schema coverage and the matching-behavior note, the definition is adequate; only sibling routing is missing.

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 all three parameters (keyword, fields, precision) are already documented in the schema, including the compact-mode semantics. The description adds nothing about `fields` or `precision`, so baseline 3 is correct.

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?

States a specific verb+resource ('Look up a dream symbol by keyword') and adds the lookup mode (exact match, falling back to partial substring). It is distinguishable from astroway_esoteric_dreams_decode and astroway_esoteric_dreams_recurring_themes by being a single-symbol keyword lookup, but it never names or contrasts those siblings explicitly.

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 when-to-use, when-not-to-use, or alternative-routing guidance. With four dream-domain siblings (dreams, dreams_decode, dreams_by_element, dreams_recurring_themes) an agent gets no help deciding between a symbol lookup and a full dream decode.

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 the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real context: deprecated status, sunset date, credit cost tier, and that the cast is unseeded random rather than reproducible. The only weak spot is the ambiguous 'input ignored' claim, which sits oddly beside two documented request parameters.

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 critical information — deprecation and replacement — is in the first sentence, and the metadata block is scannable. It is somewhat repetitive, stating DEPRECATED in the title, the first sentence, and again in a trailing warning line, which costs it a point.

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 deprecated two-parameter tool with an output schema, everything an agent needs is present: why to avoid it, what to use instead, how long it remains callable, and its cost. Return values are covered by the output schema, so nothing material is missing.

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 both `fields` and `precision` are fully documented in the schema and the description need not restate them. 'Input ignored' adds a small amount of meaning (output is not driven by request input) but does not clarify how those two parameters interact with the cast, so the baseline 3 applies.

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?

States a specific verb and resource ('Casts a single I Ching hexagram') and explicitly marks itself as the legacy un-namespaced variant, so an agent can distinguish it from the six /iching/* siblings without opening any schema. The deprecation is front-loaded in the title and repeated in the body.

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 to avoid it and names the replacement set, singling out `/iching/throw-coins` as 'seeded + reproducible' so the agent knows why it is preferred. It also gives a hard operational cutoff ('Still works until its 2027-06-16 sunset, then removed'), which is exactly the when-not-to-use detail an agent needs.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation context: a cost of 10 credits (Tier 1) and the Agrippa system grouping. It does not, however, describe response shape or any behavioral nuance beyond pricing.

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 text is short and cleanly structured with bracketed metadata, but the opening line largely duplicates the title rather than adding content, so brevity here reflects thinness rather than economy. It is front-loaded but not substantive.

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 zero required parameters and an output schema present, the description is not obligated to explain return values, and annotations cover safety. What remains missing is the fundamental statement of what invoking this tool produces, which is why it sits at minimum viability rather than higher.

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% — both optional parameters (fields, precision) are fully documented in the schema, including compact-mode semantics and rounding. The description adds nothing about parameters, so the baseline 3 applies.

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 is essentially a synonym list for the figure's name/title: 'Acquisitio: Gain' restated as 'Gain, profit, abundance.' It never states what the tool actually does (compute a geomancy figure? return an interpretation?) or how it differs from the 15 sibling geomancy figure tools. An agent learns the symbol's meaning but not the operation.

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 when-to-use, when-not-to-use, or alternative selection guidance is present. The '[Group: Geomancy (Agrippa)]' tag hints at family membership but gives no selection criteria among albus, amissio, fortuna_major, etc. This is effectively no guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the group tag and a concrete cost (10 credits, Tier 1), which is genuine behavioral context, but says nothing about authentication, rate limits, or what the figure output contains.

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?

It is short and front-loads the keyword fragment, but the content is not functional and the group/cost tags are structured metadata rather than explanatory prose. Briefness here stems from under-specification rather than disciplined concision.

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?

An output schema exists so return values need not be explained, but the description still fails to tell the agent what this tool produces or why it differs from its many geomancy siblings. For a tool in a 16-figure family, that omission is material.

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% and both parameters (fields, precision) are fully documented in the schema, so the baseline of 3 applies. The description contributes no additional 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 is a three-word keyword fragment ("Wisdom, peace, clarity.") that echoes the title "Albus: White" rather than stating what the tool does. It never says it returns the Albus geomantic figure, its interpretation, or its attributes, so an agent cannot distinguish it from the 15 sibling geomancy figures by function.

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 invoke this figure versus any of the other geomancy tools (Puer, Rubeus, Fortuna Major, etc.). No conditions, prerequisites, or alternatives are mentioned at all.

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 disclose that the tool is read-only, idempotent, non-destructive, and not open-world, so the safety profile is clear. The description adds useful context by naming the group 'Geomancy (Agrippa)' and stating a cost of 10 credits (Tier 1), but it does not add further behavioral detail beyond that.

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

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

The description is short and front-loads the thematic phrase before grouped metadata for group and cost. There is little wasted text, though the thematic phrase alone is not very informative.

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?

An output schema and full parameter descriptions are present, and annotations cover the safety profile, so the description need not explain return values or invocation mechanics. However, it remains thin on what the tool does and when to select it among many similar geomancy figure tools, leaving a meaningful contextual 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?

Schema description coverage is 100% and both parameters are fully described in the input schema. The description adds no parameter semantics of its own, so the baseline of 3 applies because the schema carries the parameter documentation.

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 the symbolic theme 'Loss, letting go, slipping away' but never states what the tool actually does, such as retrieve or interpret the Amissio geomancy figure. It largely restates the title 'Amissio: Loss' without adding an action verb or clear resource distinction from the many sibling geomancy figure tools.

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, when not to, or which sibling geomancy tool to choose instead. The thematic phrase may imply a loss-related context, but this is not explicit enough to count as 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description adds useful cost (10 credits, Tier 1) and group context, but does not disclose any additional behavioral traits such as what the returned data represents.

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

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

The description is very short, front-loaded with the figure's meaning, and includes no filler. Its only weakness is that the brevity reflects under-specification rather than efficient completeness.

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?

An output schema exists, annotations are rich, and both parameters are fully described, so the description need not cover return values or parameter syntax. However, it still fails to state the tool's purpose or usage context, leaving the agent to infer the operation from the name and title.

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 both optional parameters (fields and precision) are fully documented by the schema. The description adds no parameter-level meaning, 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 restates the title ('Dragon's Head') and adds symbolic keywords ('beginnings, threshold') but provides no action verb or statement of what the tool actually does. It does identify the specific geomancy figure among siblings, but stops short of explaining the operation.

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 given for when to use this tool versus alternatives such as other geomancy figures or contextual reading tools. The group and cost metadata are present but do not tell an agent when this figure is the right choice.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description does add genuinely useful non-schema context — it is a Tier 1 operation costing 10 credits — which tells an agent about billing/cost behavior. It says nothing about what the response contains or whether the reading is deterministic per invocation, so it earns partial credit only.

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?

It is compact and carries no filler, and the labeled [Group]/[Cost] tags give it a discernible structure. However the terseness is under-specification rather than disciplined conciseness — the fragment conveys symbolic flavor, not what the call does, so it does not fully earn 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?

An output schema exists, so return values need not be explained, and only 2 optional params exist. But with 15 near-identically-named geomancy siblings, an agent still lacks the one thing it needs: confirmation that this tool produces the Carcer figure's reading and any input convention (e.g., a chart or seed) for it. The description is complete only in the metadata sense.

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% and both parameters (fields, precision) are fully documented including examples and units in the input schema. The description adds no parameter meaning at all, so the baseline of 3 for full schema coverage applies.

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 is a keyword gloss ('Restriction, confinement, isolation') that restates the title 'Carcer: Prison' rather than stating a verb+resource. It never says the tool returns a geomancy figure reading/chart, so an agent cannot distinguish it from the 15 other astroway_geomancy_* siblings beyond the figure's name. This is effectively a tautology of the title.

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 when-to-use guidance, no prerequisites, no mention of when a caller should pick Carcer over Veritas/Via/Puella or the other geomancy figures. The only contextual hint is the bracketed Group tag, which is taxonomy rather than usage direction.

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 readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description does add genuinely useful context the annotations lack — the cost (10 credits, Tier 1) and the group membership. However, it discloses nothing about what a call actually produces.

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?

Very short and front-loaded, with the figure's meaning first and metadata bracketed below. No sentence is wasted, though the first line conveys symbolic flavor rather than operational 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?

An output schema exists, so return values need not be described, and the parameters are fully documented. What is missing is the core operational statement of what the tool does, which leaves an agent guessing at its behavior despite the otherwise adequate structured coverage.

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 both parameters (fields, precision) are already fully documented in the schema. The description adds no parameter meaning beyond that, which is the expected baseline when the schema does the heavy lifting.

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 is essentially the figure's name translated with a symbolic gloss ("Dragon's Tail: endings, exit"). It never states a verb or what the tool returns — no indication that it delivers a geomancy reading for this figure. It restates the title rather than describing a function, and does not distinguish the tool from the 15 sibling geomancy figures beyond the figure's name.

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

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

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tools are named. The symbolic gloss "endings, exit" hints at the kind of question this figure suits, which is weak implied usage, but nothing tells the agent how to choose between Cauda Draconis and Caput Draconis or the other figures.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds one genuine piece of behavioral context — the 10-credit (Tier 1) cost — plus the group tag, but says nothing about response behavior or interpretation depth.

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?

It is brief and free of filler sentences, but the sole content line is a keyword gloss that does not earn its place as functional documentation. Shortness here reflects under-specification rather than disciplined concision.

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 an output schema exists, return values need not be explained, but the description still omits the most basic fact an agent needs: what invoking this tool produces and in what context to invoke it. For a domain-specific divination tool surrounded by many near-identical siblings, this is a significant 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?

Schema description coverage is 100%, so both optional parameters (fields, precision) are fully documented in the schema itself. The description adds no additional parameter meaning, which is the expected baseline when the schema carries the burden.

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 the symbolic meaning of the Coniunctio figure ("Union, meeting, partnership") but never states what the tool actually does — no verb, no resource, no indication that it returns a geomancy reading. It reads as a glossary gloss of the name rather than a functional description, so an agent cannot distinguish its operation from the other fifteen geomancy figure siblings beyond the keyword.

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 when-to-use guidance, no conditions, and no mention of alternatives among the many sibling geomancy figures. The only extra context is group/cost metadata, which does not tell an agent when this tool is the right choice.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful non-annotation context — the 10-credit Tier 1 cost and the Agrippa group — but says nothing about what the reading contains or how it is produced.

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 short lines, front-loaded, with no filler. The group and cost tags earn their place as billing/routing context; the only weakness is that the brevity comes at the cost of substance rather than being tight specification.

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 an output schema present, return values need not be explained, but the description still fails to say that this is a geomancy figure lookup, how it differs from the fifteen sibling geomancy figures, or what a caller gets back. For a 17-figure family with near-identical definitions, that gap is material.

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 both optional parameters (fields, precision) are fully documented in the schema with examples and defaults. The description adds nothing about them, which is the expected baseline when the schema does the heavy lifting.

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 'Greater Fortune: lasting success' restates the figure's name and gives its traditional meaning, but never states what the tool does — no verb such as 'return the geomancy reading for the Fortuna Major figure'. An agent must infer the operation entirely from the name and sibling pattern.

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 when-to-use guidance, no condition for choosing this figure over the sibling figures (e.g. fortuna_minor, laetitia, tristitia), and no mention of inputs or prerequisites. The [Group] and [Cost] lines describe metadata, not usage.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context the annotations don't carry — cost (10 credits, Tier 1) and group membership — but says nothing about what the call produces or requires.

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?

It is short and front-loaded, with the cost/group tags being the only structured metadata. However, the brevity stems from under-specification rather than efficient information density — the two fragments earn their place but carry very little.

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 divination tool in a crowded geomancy family with an output schema, the agent still cannot tell what this tool returns, what makes it distinct from fortuna_major, or what situation calls for it. The output schema covers return values, but the invocation context is largely missing.

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% for both 'fields' and 'precision', so the schema fully documents the parameters. The description adds no parameter meaning beyond that, which is the expected baseline of 3 when the schema does the heavy lifting.

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 the figure and gives an interpretation gloss ('Lesser Fortune: quick gains'), but never states what the tool actually does — no verb like 'returns/draws/casts a reading'. It also fails to distinguish itself from the sibling astroway_geomancy_fortuna_major, which it most needs to be differentiated from.

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 the fifteen other geomancy figure siblings or fortuna_major. Usage is only implied by the figure name, and no conditions, prerequisites, or exclusions are stated.

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 the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description's burden is lower. It adds genuinely non-annotated context — the credit cost (10 credits, Tier 1) and the Agrippa grouping — but says nothing about what a call yields or how it behaves.

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 text is short, front-loaded and free of padding, which is good structurally. However it is arguably undersized for a tool that must be distinguished from 15 sibling geomancy figures, so brevity comes at the cost of usefulness.

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 an output schema and full annotation coverage, the description need not explain return values, but it still omits the core fact of what the tool produces and how it differs from sibling figures. For a one-of-many esoteric lookup, that gap leaves the definition materially incomplete.

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?

Both optional parameters (fields, precision) are fully documented in the schema at 100% coverage, so the schema carries the semantics. The description adds nothing about how to use compact mode or precision, making this a baseline 3.

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 is a keyword gloss of the figure's meaning ('Happiness, optimism, healing') that essentially restates the title 'Laetitia: Joy'. It never states the tool's action — e.g. that it returns a geomancy reading/interpretation for the Laetitia figure — so an agent cannot tell what it actually does versus its 15 geomancy siblings.

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 when-to-use guidance, no mention of alternatives among the many astroway_geomancy_* siblings, and no prerequisites or exclusions. Only the group tag and credit cost are provided, which do not help an agent choose this tool over a sibling figure.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds genuine context beyond that — the '[Group: Geomancy (Agrippa)]' taxonomy and the '[Cost: 10 credits (Tier 1)]' billing tier — but says nothing about what the response contains or any auth/quota 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?

It is short and front-loads the figure's semantic keywords before the bracketed metadata, with no wasted sentences. However, it is under-specified rather than genuinely concise — the terseness leaves the operation undefined.

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?

An output schema exists, so return values need not be explained, and annotations fully cover the safety profile with zero required parameters. The remaining gap is the missing statement of what the tool actually produces, which is significant but partly mitigated by the structured fields carrying the rest.

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% for both optional parameters (fields, precision), and their schema descriptions are detailed and self-sufficient. The tool description contributes nothing about parameters, so the baseline 3 applies.

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 is a bare keyword dump ('Crowd, gathering, public') that restates the title 'Populus: The People' rather than stating a verb+resource operation. It never says what calling the tool does (e.g., returns the Populus geomantic figure and its reading), so an agent cannot tell it apart from the other fifteen astroway_geomancy_* figure tools on anything but the name.

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

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

There is no when-to-use or when-not-to-use guidance, no mention of alternatives among the geomancy siblings, and no indication of what question or context should trigger this figure. The only contextual metadata is group and cost, which is not 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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, and an output schema exists, so the safety/return burden is covered. The description does add genuinely useful non-annotation context: the group provenance and the cost (10 credits, Tier 1), which matters for a metered API. It stops there, adding nothing about what the figure reading contains.

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 text is tightly sized and cleanly front-loaded (meaning first, then bracketed metadata tags), with no filler. It is short rather than bloated, though the brevity reflects under-specification rather than disciplined economy.

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 single-figure lookup tool the description should at minimum state what is returned and why an agent would pick Puella over puer or fortuna_major. Neither is present, and the sibling set offers no compensating signal. Annotations and the output schema soften the impact, but the core functional statement is missing.

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%: both 'fields' (compact dotted-path projection) and 'precision' (decimal rounding) are fully documented in the schema itself. The description adds no parameter meaning beyond that, so the baseline of 3 applies.

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 'Beauty, harmony, love' is the traditional meaning of the geomantic figure Puella, not a statement of what the tool does. It never says it returns a Puella figure reading, interpretation, or geomancy result, so an agent cannot infer the tool's operation from the text. It also fails to distinguish this figure tool from its 15 geomancy siblings (puer, albus, rubeus, etc.).

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 when-to-use guidance, no condition for choosing Puella over the other 15 geomantic figure tools, and no prerequisites stated. The [Group: Geomancy (Agrippa)] tag only categorizes it; it does not route the agent.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description's genuine addition is the credit cost (10 credits, Tier 1) and the group membership, which is useful operational context. It adds nothing about what the response contains, though an output schema 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 short fragments with no wasted words and the symbolic meaning front-loaded. However, the brevity comes at the cost of substance rather than being efficiently dense – there is little of value to compress.

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 annotations covering behavior, an output schema covering returns, and a fully documented schema, the one thing the description must supply is what distinguishes this tool from its many geomancy siblings – and it does not. It never states the operation performed or the selection criteria, leaving the agent unable to choose among the 16 sibling figures.

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% for both optional params (fields, precision), and their descriptions are self-explanatory. The description adds no parameter meaning, so the baseline 3 for fully documented schemas applies.

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 "Young man, energy, impulse" restates the title's symbolic keywords rather than stating an action or resource. It never says what the tool actually does (presumably return a geomancy reading for the Puer figure), so an agent learns the figure's meaning but not the tool's function. This is close to tautology against the name/title.

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 when-to-use guidance, no conditions, and no mention of alternatives. With 16 near-identical geomancy siblings (Puella, Rubeus, Albus, etc.) sharing this shape, the absence of any routing guidance is a serious gap.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description does add genuinely useful non-schema context — the 10-credit (Tier 1) cost and Agrippa system grouping — but says nothing about the response shape or any behavioral edge cases beyond that.

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

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

Extremely tight — one evocative clause plus bracketed metadata tags, with no filler. Nothing is wasted, though the brevity is partly under-specification rather than pure economy.

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?

An output schema exists so return values need not be explained, and annotations cover safety, but the core purpose — what the tool returns and how it differs from its many geomancy siblings — is absent. For a figure-lookup tool in a crowded sibling set, the description is not complete enough to select it confidently.

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%: both optional parameters (fields, precision) are fully documented in the schema with examples and defaults. The description contributes nothing about parameters, which is the expected baseline 3 when the schema does all the work.

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 evocative keywords for the Rubeus figure ('Passion, anger, blood: ill omen') but never states what the tool actually does — no verb, no 'returns the meaning of the Rubeus geomantic figure'. With 15 sibling geomancy figure tools distinguished only by name, an agent gets thematic flavor but no functional statement of 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?

There is no when-to-use guidance, no mention of how it relates to the other fifteen geomancy figure tools (e.g. whether it returns just this figure's interpretation), and no prerequisites or alternatives. The Group and Cost tags are metadata, not usage direction.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description does add two genuinely useful behavioral facts not in the annotations: the group ([Geomancy (Agrippa)]) and the cost (10 credits, Tier 1). It still says nothing about what the call returns or what triggers it, but with annotations carrying the safety burden a 3 is fair.

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 minimal and front-loaded, and the bracketed metadata tags are cleanly structured. However, the three-word body is under-specified rather than genuinely concise — the brevity comes at the cost of the tool's core explanation.

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?

An output schema exists, so return values need not be explained, and annotations cover safety. But for a tool with no required parameters whose purpose is entirely unstated, the description leaves the agent unable to know what invoking it actually produces or when it should be chosen over the 15 sibling geomancy tools.

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% and both parameters (fields, precision) are fully documented in the schema itself. The description adds no parameter guidance whatsoever, which is acceptable given the schema does the work, but earns no credit above baseline.

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 is "Sadness, depression, melancholy." — a list of the figure's symbolic meanings rather than a statement of what the tool does. It effectively restates the title ("Tristitia: Sorrow") and never uses a verb or names a resource, so an agent cannot tell whether it returns an interpretation, a chart placement, or a description of the geomantic figure.

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 when-to-use guidance, no prerequisites, and no mention of the 15 sibling geomancy figure tools it competes with. The only routing signal is the implicit keyword match on the figure's meaning, which the agent must infer on its own.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful operational context beyond the annotations: the group ('Geomancy (Agrippa)') and the cost ('10 credits (Tier 1)'). It still says nothing about the output form or whether the result is static, but the cost disclosure earns partial credit.

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?

It is short and the operative theme is front-loaded, with metadata tagged at the end. However, the extreme terseness reflects under-specification rather than economy: the text is too thin to convey purpose or routing, so the brevity does not fully 'earn 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 is simple: two optional formatting params, full schema coverage, an existing output schema (so return values need no explanation), and annotations covering safety. Against that low complexity a minimal description is tolerable, but the total lack of differentiation from fifteen sibling figure tools leaves an agent unable to route to this tool confidently.

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%, and both parameters (fields, precision) are fully documented in the schema with usage examples and defaults. The description adds no parameter semantics at all, so the baseline of 3 applies given the schema carries the full burden.

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 only thematic keywords ('Movement, change, journey') that restate the esoteric meaning of the name/title 'Via: The Way' rather than stating what the tool does. There is no verb and no resource, so an agent cannot tell whether it returns an interpretation, a chart, or a lookup. It also fails to distinguish this tool from its fifteen near-identical geomancy siblings (puer, albus, laetitia, etc.).

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 when-to-use guidance, no prerequisites, and no mention of any alternative. With fifteen structurally identical geomancy figure tools listed as siblings, the absence of any selection criteria is a serious gap. Nothing tells the agent when 'Via' is the right figure vs. any other.

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 readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds two genuinely new facts — determinism (same question yields the same hexagram) and a 10-credit cost — but says nothing about output shape beyond what the output schema provides.

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 tight lines, with the core purpose front-loaded before the bracketed group and cost metadata. Nothing is padded, though the boilerplate bracket tags carry little decision 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?

An output schema exists, so return values needn't be described, and annotations cover the safety profile. What remains missing is sibling differentiation among five I Ching tools and any semantics for the required question input, leaving the agent to guess at routing.

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%: fields and precision are documented in the schema, but the required 'question' parameter has no schema description and the tool description only says 'from question text', adding no constraints or format guidance (2-500 chars). Baseline 3 is appropriate, with a small gap on the required 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?

States a specific output (a hexagram) derived from a specific input (question text), and 'deterministic' hints at how it differs from sibling tools like throw_coins. However, it never names a sibling, so an agent must infer the distinction rather than being told it.

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 explicit when-to-use guidance or routing against the four sibling I Ching tools (daily, lookup_number, throw_coins, with_changing_lines). The word 'deterministic' implicitly contrasts with a random-cast tool, but nothing tells the agent which condition selects this tool.

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 readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description adds that the result is deterministic per date, which usefully reinforces the idempotent hint, and gives a credit cost. It does not describe the return shape or any auth/quota behavior beyond cost.

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 core sentence is front-loaded and terse with zero padding, and the group/cost lines are compact structured metadata. It is efficiently sized, though the one-line purpose is arguably too thin for a tool with three parameters.

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?

An output schema exists so return values need not be explained, and annotations cover the safety profile. However the description leaves the date format and sibling routing unaddressed, which are the main things an agent still needs to invoke it 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 coverage is 67%: fields and precision are documented in the schema, but the date parameter has no schema description. 'per-date' tells the agent date matters but never gives a format (ISO date, timezone, etc.), so the description only partially compensates for the undocumented 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?

States a specific resource (hexagram) and a clear scope modifier (per-date, deterministic), which separates it from the random astroway_iching_throw_coins and the question-driven astroway_iching_by_question. It does not explicitly name a sibling, but 'per-date' and 'deterministic' make the purpose legible enough to distinguish it from the other I Ching tools.

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 word 'daily' and 'per-date' imply the intended use case (get the hexagram for a given day), but there is no explicit when-to-use, when-not-to-use, or routing to alternatives like astroway_iching_lookup_number or astroway_iching_with_changing_lines.

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 readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is fully covered. The description adds one genuinely useful behavioral fact — that cost is not in the public credit manifest, so billing is plan-dependent — but says nothing about response shape or limits.

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 core sentence is short, front-loaded, and waste-free. The bracketed Group/Cost tags are boilerplate but compact and carry real information (cost uncertainty).

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 an output schema, rich annotations, and full schema coverage, the description only needs to nail purpose and routing. Purpose is clear, but among six I Ching siblings an agent would benefit from a routing hint that this is the direct-lookup path rather than a reading/casting path.

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 explains number, fields, and precision in detail. The description adds no parameter meaning beyond what the schema provides, which is the baseline 3 case.

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?

States a specific verb ('Fetch') and resource ('hexagram 1-64') with the keying scheme ('by King Wen number'), so the agent knows exactly what this returns. It does not explicitly distinguish itself from the I Ching siblings (throw_coins, by_question, daily, with_changing_lines), but the 'by number' lookup is inherently distinct.

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 versus the four other I Ching tools, no prerequisites, and no exclusions. The only contextual line is a cost caveat, which is not 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, covering safety and determinism. The description adds the 'seeded' nature (explaining idempotency) and a cost of 10 credits, which are useful behavioral details 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 very short and front-loads the method name, with no wasted prose. However, for a tool with three parameters and an output schema, it is arguably under-specified rather than appropriately sized, falling short of what a concise-yet-informative description should include.

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 (3 parameters, output schema present, multiple I Ching siblings), the description is incomplete. It does not explain what the tool returns (though the output schema covers that) and, more importantly, provides no guidance on selecting it over other I Ching tools or on how the seed affects results.

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 67%: the fields and precision parameters are well documented in the schema, but the seed parameter has no schema description. The word 'Seeded' in the description hints that seed controls randomness, but it does not explain the anyOf number/string format or compensate for the missing schema description.

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 'Seeded 3-coin method' restates the tool name/action with a qualifier and does not state what the tool actually produces (e.g., an I Ching hexagram or reading). It fails to distinguish this tool from sibling I Ching tools like astroway_iching or astroway_iching_with_changing_lines.

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, and no prerequisites. The only context is a group tag and a cost tag, neither of which tells an agent when this specific coin-throwing method is appropriate.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed world, so the safety profile is covered. The description usefully adds cost (10 credits, Tier 1) and group membership, but does not explain what a 'changing line' produces or how the transformed hexagram is derived.

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?

Extremely short and front-loaded, with the core output concept stated first and metadata tags after. Nothing is padded, though the brevity shades into under-specification rather than true economy.

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?

An output schema exists, so return values need not be explained, and there are no required parameters. However, for a divination tool with an unexplained seed input, the description leaves the agent without enough conceptual grounding to choose or invoke it confidently.

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?

Coverage is only 67%, and the single undocumented parameter is `seed`, which is the semantically critical input for a divination tool (it controls determinism of the cast). The description says nothing about any parameter, so it does not compensate for the gap the schema leaves.

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 fragment 'Primary + transformed hexagrams' identifies the resource (hexagrams) and the distinguishing feature (a transformed hexagram produced by changing lines), which loosely separates it from astroway_iching. But it never states a verb or action ('cast', 'generate', 'read') and reads as an output label rather than a purpose statement.

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 when-to-use guidance, no prerequisites, and no mention of the sibling I Ching tools (iching_throw_coins, iching_by_question, iching_daily, plain iching). The only routing signal is the implicit 'changing lines' concept in the name, which the description does not explain.

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

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description goes further by disclosing input processing behavior (vowel points and cantillation stripped) and output ambiguity handling (final letters returned as both ordinary and 500-900 forms rather than a single choice), which is genuine context 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?

Two dense, front-loaded sentences that carry the cipher list, the preprocessing rule, and the final-letter ambiguity rule with no filler. The trailing group/cost metadata is standard boilerplate.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The main parameter's semantics are well covered; the only gap is that the optional compact-mode parameters (`fields`, `precision`) are addressed only in the schema, not 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?

Schema coverage is 67%; `fields` and `precision` carry their own schema descriptions, while `text` has none. The description compensates by explaining how the Hebrew input is interpreted (stripped vowel points, final-letter handling), adding real semantic meaning to the required parameter beyond the bare string type.

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 precise operation (computing seven named ciphers over a Hebrew text) and enumerates the exact ciphers: absolute, large, small, ordinal, inclusive, AtBash and AlBam. This clearly distinguishes it from the Kabbalah siblings (sephiroth, shem_names) and from other esoteric tools.

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 scope makes the applicable use case inferable, but there is no explicit when-to-use statement, no prerequisites, and no named alternative or exclusion. The agent must infer applicability from the domain description alone.

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 readOnly, idempotent, non-destructive, non-open-world behavior. The description adds genuine additional context beyond that: the data is static and pre-computed, and the response itself signals this, which matters for an agent deciding whether results are deterministic.

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 tight sentences, front-loading the resource and its contents, followed by bracketed group/cost metadata. Every sentence earns its place with no padding.

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?

An output schema exists, so return-value explanation is unnecessary, and annotations cover the safety profile. The description is complete enough for a static reference tool, though a hint tying it to related kabbalah lookups would close the last 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?

Schema description coverage is 100%, so the `fields` and `precision` compact-mode parameters are fully documented in the schema. The description adds no extra syntax or semantics for them, 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 names a concrete resource (the Tree of Life sephirot table) and enumerates its columns (Hebrew, meaning, pillar, triad, Golden Dawn planetary attribution), so an agent knows exactly what it retrieves. It is clearly a distinct static reference versus siblings like gematria or shem_names, though it does not name them explicitly.

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 line 'Nothing here is computed' implies this is a pure static lookup to be used when the sephirot reference is needed, but there is no explicit when-to-use or when-not-to-use versus kabbalah_gematria or kabbalah_shem_names. Usage is only 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and non-destructive, so the safety profile is covered. The description adds the genuinely useful computation-method detail and the 5-credit cost, but omits any note on result size, pagination or why filtering matters.

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 compact sentences front-load the core identity and derivation, then the filter syntax. The bracketed [Group] and [Cost] tags are lightweight metadata rather than prose padding.

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?

An output schema exists, so return values need not be explained, and both real parameters are documented in the schema. The unresolved mismatch between the advertised ?index/?longitude filters and the actual schema leaves an invocation gap for a no-required-parameter 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% for the two real parameters (fields, precision), so the baseline would be 3. However, the description advertises filter parameters ?index and ?longitude that do not exist anywhere in the input schema, which can mislead an agent about how to invoke the tool.

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 the specific resource (the 72 three-letter names / Shem HaMephorash), states how it is derived (computed from Exodus 14:19-21, not table lookup) and what it returns (each with its five zodiacal degrees). That clearly separates it from siblings like astroway_kabbalah_gematria and astroway_kabbalah_sephiroth, though the phrasing is a noun phrase rather than an explicit verb.

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 gives a usage hint for filtering (index 1..72 or longitude 0..360) and discloses the credit cost, but never says when to choose this tool over the other Kabbalah or esoteric siblings, and offers no exclusions or prerequisites.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description does add two genuinely useful behavioral facts — that the label is not unique beyond the 52-year cycle and that the call costs 10 credits (Tier 1) — but says nothing about the returned structure or the assumed calendar.

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 core semantics are front-loaded into a single tight sentence, with group/cost metadata relegated to bracketed tags. Nothing is wasted, though the tags are structured metadata rather than description prose.

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?

An output schema exists, so return values need no explanation, and the annotations cover the safety profile. What is still missing is the calendar assumed by the 'date' input (Gregorian vs. other) and any indication of when to prefer this over the standalone tzolkin/haab tools.

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 67%; the two optional params (fields, precision) are fully documented in the schema, while 'date' is only constrained by a pattern. The description adds no parameter meaning at all, so this sits at the baseline for a mostly-covered 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?

States a specific computed artifact — a combined Tzolkin + Haab date label — and its scope (unique within the 52-year / 18,980-day cycle). The word 'Combined' implicitly sets it apart from the sibling astroway_mayan_tzolkin and astroway_mayan_haab tools, though it never names them directly.

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 when-to-use statement, no prerequisites, and no explicit routing to or away from the individual tzolkin/haab siblings. The only hint is the adjective 'Combined', which is too thin to count as guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the scored-output behavior (0-100) and the cost/10-credit tier, which is useful context, but says nothing about input requirements or result semantics beyond the score. 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?

Two tight sentences lead with the mechanism and immediately give the output range, with group and cost metadata on separate lines. No filler, though the description is short enough that it leaves usage and input gaps unaddressed.

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?

An output schema exists, so the return payload needn't be described, and annotations carry the safety profile. However, for a tool with a nested person1/person2 input object and no usage guidance, the omission of any explanation of how the two dates are consumed leaves the definition only minimally 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 coverage is only 50% and the two required parameters (person1.date, person2.date) have no descriptions in either schema or description. Worse, the description frames inputs as 'Tzolkin name + tone' while the schema actually accepts birth dates, which does nothing to clarify parameter meaning; fields and precision are only documented in 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?

States a specific verb+resource (pair compatibility) and the computation basis (Tzolkin name + tone alignment plus elemental/directional affinity), plus the output shape (0-100 score). It is clearly a two-person tool, distinguishing it from the single-chart Mayan siblings like tzolkin or haab, though it never names those siblings explicitly.

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 when-to-use or when-not-to-use guidance and no explicit routing to alternatives such as astroway_mayan_full or astroway_mayan_tzolkin. The pair framing implies a relationship scenario, but the agent gets no condition that selects this tool over the other Mayan tools.

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

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

Annotations already disclose readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description adds genuinely useful non-schema context: the credit cost ('10 credits (Tier 1)'), the group tag, and the returned components, which agents need for planning.

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 tightly-wound sentences, front-loaded with the identity and return shape, followed by the differentiating clause. The bracketed group/cost metadata is compact and useful rather than padding.

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?

An output schema exists, so return detail is covered elsewhere, and the description still summarizes the return ('kin + tone + seal'). Combined with annotations and the cost/group tags, this is complete enough for a read-only lookup tool; only the date format is left entirely to the schema.

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%: 'fields' and 'precision' are documented in the schema, while 'date' carries only a regex pattern. The description adds no meaning about the date format or the compact-mode params, so it neither compensates for the gap nor extends the schema. Baseline 3 for schema-led params.

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?

States a specific resource (the Argüelles Dreamspell reinterpretation) and a specific verb/output ('Returns kin (1-260) + tone + seal'). The line 'Distinct from traditional Tzolkin' explicitly separates it from the astroway_mayan_tzolkin sibling, so an agent can route correctly without opening any 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 'Distinct from traditional Tzolkin' clause tells the agent when to pick this modern variant versus the traditional one, which is the key selection decision among the Mayan siblings. It stops short of an explicit when/when-not rule or naming other siblings like mayan_full or mayan_calendar_round.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value by disclosing the cost ('10 credits, Tier 1') and the fact that five results are bundled, but it says nothing about response shape beyond the component list and contains the four-vs-five component inconsistency.

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 the payload description, followed by short bracket-tagged group and cost metadata. Compact and mostly waste-free, though the bracketed metadata lines are not part of the functional description.

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 an output schema present, the description need not explain return values, and annotations cover the safety profile. It adequately conveys what the tool produces and its cost; the only gap is routing guidance against the seven sibling Mayan tools.

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 67%: `fields` and `precision` carry detailed descriptions while `date` relies only on its YYYY-MM-DD regex pattern. The description adds no parameter guidance at all, so it does not compensate for the undocumented `date` parameter, though the schema largely self-documents the compact-mode options.

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: it returns the bundled Mayan date components, enumerating Long Count, Tzolkin, Haab, Calendar Round and Lord of the Night. This clearly distinguishes it from the single-component siblings (astroway_mayan_long_count, astroway_mayan_tzolkin, etc.), though it never names those siblings explicitly. Minor flaw: it says 'four classical components' while listing five items.

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 phrase 'in one call' implies this is the aggregate alternative to invoking the individual Mayan component tools, but there is no explicit when-to-use/when-not guidance and no named alternatives. Usage is inferable rather than stated.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds genuine context the annotations cannot: the calendar's composition (18×20 + 5) and the cost tier of 10 credits, which is a real behavioral trait. It does not, however, disclose response shape, precision defaults, or whether the result is deterministic across the same date.

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 tight lines front-load the calendar definition and the Wayeb highlight, followed by compact group/cost tags – no filler sentences. It is efficient, though the terseness comes partly from omitting the actionable verb and routing 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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, for a tool sitting among seven Mayan siblings with no sibling routing and an undescribed required date parameter, the definition leaves meaningful gaps an agent would want closed before invoking 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?

Schema coverage is only 67%, and the required 'date' parameter carries a regex pattern but no textual description; the description says nothing about accepted date format, timezone handling, or valid ranges. The two documented parameters are generic 'compact mode' options unrelated to this calendar, so the description adds no parameter-level meaning for the tool's actual input.

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 the resource (the 365-day Haab civil calendar) and states one concrete function – detecting whether the date falls in the 5-day Wayeb period – but never phrases the core action (computing the date's Haab position) as a verb. With seven Mayan siblings (mayan_full, mayan_tzolkin, mayan_calendar_round, etc.), it offers no differentiation, so an agent cannot tell which Mayan tool to pick from this text alone.

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 when-to-use guidance, no exclusions, and no mention of alternatives such as mayan_full (which plausibly subsumes the Haab) or mayan_tzolkin. The 'Wayeb' sentence implies one reason to call it but stops short of routing advice.

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