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 genuine domain behavior: the whole-sign counting rule, the Sun-sign fallback when the birth time is absent, and the traditional-ruler-plus-modern-co-ruler convention. It does not discuss return format mechanics, but the substantive 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?

A single front-loaded sentence that opens with the purpose and then unpacks the returns; no filler. It is dense with stacked clauses, which is efficient but slightly hard to scan compared to a split form.

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

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

With no output schema and nine parameters, the description carries the return-value burden and discharges it by enumerating the house, sign, lord of the year, lord's location, and date range. Nothing an agent needs to decide to call it or interpret results 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 every parameter (age, on_date, city, time, timezone, house_system, etc.) is already documented in the schema, including age's precedence over on_date. The description only restates the age-or-date framing and the unknown-birth-time behavior, so the 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?

Names a specific technique (Hellenistic annual profection) and enumerates exactly what it computes: profected house, its sign, lord of the year with modern co-ruler, the lord's natal placement, and the year's start/end dates. It is unmistakably distinct from siblings like natal_chart or transits.

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?

States it can be run 'for an age or a date' and gives the key conditional: whole-sign from the Ascendant, or from the Sun's sign if birth time is unknown. It does not explicitly route against the sibling tools (transits, natal_chart), so it falls short of a full when/when-not statement.

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 openWorld=false, so safety is covered. The description adds genuine context beyond that: temporal precision ('to about a minute'), UTC plus a chosen time zone, and the fact that station degrees and signs are included in the output.

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 front-loaded sentence with no filler; the parentheticals carry real information (default range, precision, time zone, station data) rather than padding. Slightly dense, but every clause earns its place.

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

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

With no output schema, the description carries the burden of describing returns, and it does so by naming the four time points plus degree/sign data and the time zone handling. Combined with the fully documented schema, an agent has everything needed to call and interpret this tool.

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

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

Schema coverage is 100%, so all three parameters are already documented with defaults, patterns, and the 30-year cap. The description only restates the default range behavior, adding little beyond what the schema provides. 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 (Mercury retrograde periods) and a precise scope (overlapping a date range), then enumerates the exact artifacts returned: pre-shadow start, both stations, and post-shadow end. This is clearly distinguishable from siblings like moon_phase or transits.

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 by the astronomy domain and the defaults ('default: the next 12 months'), but there is no explicit when-to-use guidance or routing against siblings such as transits or moon_phase. An agent can infer intent but receives no conditional steering.

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 adds genuinely new behavior: the default-to-now semantics and, importantly, the full set of computed return fields — which matters because there is no output schema to carry that information.

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

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

A single sentence, front-loaded with the resource and the default, with no filler. The long tail enumerating return fields is justified given the absence of an output schema, though the comma list is dense and could be grouped more readably.

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 zero-required-parameter, read-only lookup with no output schema, the description supplies both the default behavior and the shape of the result, which is precisely the information the agent lacks from structured fields. Nothing needed to call it correctly 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 date/time/timezone formats and defaults are already fully documented in the schema. The description only echoes the 'default: now' behavior and adds no new syntax, format, or interaction details (e.g., how date and time combine, or timezone handling when only a date is given).

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 (the Moon's phase) and a specific moment in time, and enumerates exactly what is computed: phase name, illuminated fraction, Sun–Moon angle, days since new moon, signs, and upcoming quarter phases. It is clearly a distinct astronomical lookup versus the natal/transit/synastry siblings, though it never explicitly contrasts itself with them.

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 rather than stated: '(default: now)' signals that omitting the date yields the current moment, which is reinforced by the schema's 'Omit for the current moment.' There is no explicit when-to-use, when-not-to-use, or alternative-tool routing (e.g., versus transits for a time range).

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 bar is met. The description adds genuine behavioral context: graceful degradation when time is omitted (no angles or houses), the default house system, and the Placidus fallback inside the polar circles. It stops short of stating validation errors or precision caveats.

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 dense output-defining sentence followed by a short caveat sentence; every clause carries information and the most important content (what the chart contains) is front-loaded. No filler or redundancy.

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

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

With no output schema, the description bears the burden of explaining return contents and does so thoroughly, including the degraded no-time case. The main remaining gap is that the schema/description interact only loosely on timezone-vs-city precedence, but that is covered by the parameter descriptions themselves.

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 seven parameters are already documented in the schema, including the city shortcut, coordinate conventions, and house_system enum with its polar fallback. The description adds only the no-time behavior, which the schema already states for `time`; 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 ('Cast a tropical natal (birth) chart') and enumerates the exact outputs (planets with sign/degree/house/retrograde, Ascendant, Midheaven, house cusps, aspects with orbs, element/modality dominance). This clearly separates it from siblings like transits and synastry, which compute charts for other reference frames or pairs.

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 by the name and the closing note that the tool still works without a birth time, which tells the agent partial input is acceptable. However, it never names alternatives or states a when-to-use condition relative to siblings such as transits or synastry, so the routing guidance is left 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 readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds meaningful behavioral context beyond that: concrete orb thresholds per aspect type and an explicit disclaimer that the result is a descriptive tally, not a compatibility score, which manages output expectations.

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 dense sentence that front-loads the core action and then enumerates outputs in a clear parenthetical list. It is information-rich with no filler, though the length slightly favors completeness over brevity.

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

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

With no output schema, the description steps in to describe return content (aspects with orbs, planet-in-house placements, tally), and the input schema fully documents the two nested birth-data parameters. Combined with annotations covering safety, an agent has everything needed to call 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 description coverage is 100% and both parameters are richly documented nested objects (date, time, city shortcut, coordinates, timezone, house_system), so the schema carries the semantic load. The description adds only a passing reference to Ascendant implying time may matter, which the schema already explains in more 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?

States a specific verb ('Compare') and resource ('two natal charts'), and immediately scopes the output: major aspects, house overlays, and a descriptive tally. The 'two charts' framing cleanly separates it from the single-chart natal_chart sibling without needing to name 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?

The purpose implies the use case (relationship/relational analysis between two people), but there is no explicit when-to-use guidance, no exclusions, and no pointer to alternatives such as natal_chart for a single person or transits. Usage is inferred 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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds the 'omit natal to get only positions' behavior and default scoping, which is useful, but says nothing about performance, precision limits, or how the two modes differ in output shape.

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 dense sentence that front-loads the core output and then qualifies it with the optional natal comparison. Nothing is wasted, though the run-on construction packs orb, aspects, and houses into one clause.

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 complex tool with a nested natal object and no output schema, the description enumerates the main returns (positions, major aspects within orb, natal houses) so an agent knows what to expect. It stops short of describing the response structure, but the rich schema and annotations carry most of the remaining burden.

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 every parameter, including patterns, defaults and the Placidus fallback. The description restates the two key defaults (now, 2°) but adds no syntax or constraint detail beyond the schema, making baseline 3 appropriate.

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

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

The description states a specific computation (planet positions for a date/time) and its conditional extension (transit-to-natal aspects within an orb, plus transiting-house placement), which is enough for an agent to grasp the resource. It distinguishes the tool from natal_chart by describing the comparison-against-natal behavior, but never names the siblings it should be chosen over.

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: the phrase 'given a natal chart' signals the optional comparison mode, and defaults (now, 2° orb) are stated, but there is no explicit when-to-use-this-vs-alternatives guidance. An agent must infer that transits is for current/forward-looking positions while natal_chart handles the birth chart.

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