Kundaly — Vedic astrology

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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lowered. The description adds real value beyond them by disclosing the computation basis: festivals are dated by the tithi at sunrise in India (IST), which affects how the results should be interpreted. It still says nothing about result freshness or caching.

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

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

Two sentences with no filler; the resource and scope are front-loaded and the parameter's allowed values are attached compactly at the end. 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 an output schema present, return values need not be explained, and the description covers what is produced, the time window, the calendar convention, and the parameter values. Only minor gaps remain (default horizon behavior, no sibling 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?

The single horizon parameter has 0% schema description coverage and no enum constraint, so the schema alone leaves the agent guessing. The description compensates by enumerating the accepted values ('week' or 'month'), which is exactly the missing information. It does not cover the default or the exact date boundary used.

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 (Hindu festivals and observances/vratas) with a defined scope (coming week or month) and the dating rule (tithi at sunrise, IST), so the agent knows exactly what comes back. It never names or contrasts itself with siblings like panchang or monthly_forecast, 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?

The description ties the tool to a 'coming week or month' window, which implies when it is useful, and the horizon parameter hints at the two modes. There is no explicit when-to-use/when-not guidance and no routing against panchang or monthly_forecast, which is the most plausible confusion set.

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/openWorld, so the safety profile is covered. The description adds genuinely new behavior: sidereal (Lahiri) computation from the birth moment, degradation of results when birth time is unknown, and an explicit privacy guarantee that details are used for this answer only and never stored.

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 purpose, then parameter formats, then the privacy note; every sentence carries content. The parenthetical clauses make the middle section denser than ideal, but 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?

An output schema exists, so return values need no explanation, and the description covers the actionable gaps: input formats, the optional-time degradation case, and data handling. The only omission is routing against the sibling tools, which for a 3-param natal-chart tool is a minor gap.

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

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

Schema description coverage is 0%, so the description must carry all parameter meaning — and it does: YYYY-MM-DD for birth_date, city+country with the example "Pune, India" for birth_place, HH:MM 24-hour local-at-birth-place for birth_time, plus what happens when the optional one is omitted.

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 a Vedic birth star (janma nakshatra/pada), Moon sign, and ascendant — and names the exact inputs it derives them from. The natal-chart scope is inherently separable from the daily-almanac and forecast siblings, so an agent needs no further cue to pick 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?

Gives clear conditional context: supply birth_time when known, omit it if unknown, and it explains the consequence of omitting it (no ascendant; Moon may be one of two signs/stars). It does not, however, compare itself to alternatives or state exclusions relative to a different 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/non-destructive, and the description adds substantive behavior beyond them: dates are in IST, results cite Phaladīpikā ch. 26 per verse, both Moon signs are handled where a star spans two, and the reading is explicitly general rather than individual. It does not discuss caching, rate limits, or error behavior, but the transparency is well above the annotation baseline.

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 purpose and scope are front-loaded in the first clause, followed by the contents and then a compact parameter glossary. The prose is dense and sentence-long but every clause carries information about what is returned or accepted.

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 re-explained; the description still adds the structural detail an agent needs (what sections the forecast contains, IST dating, dual Moon-sign handling) plus full parameter value guidance. Nothing essential for correct invocation appears to be 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 0%, so the description must carry all parameter meaning, and it does: birth_star is any of the 27 nakshatras acceptany common spelling, ascendant is a sign in English or Sanskrit, and month is 'current' or 'next' — supplying value-space information the schema's plain string types lack.

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

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

The description names a specific verb and resource: a monthly Vedic transit forecast for a given birth star and ascendant, enumerating the delivered artifacts (planetary moves with dates, house crossings, classical results, tārā). It clearly differs from siblings like panchang or festivals by output content, but it never explicitly names or excludes those 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?

Usage is implied — you call it when you want a month-scoped forecast for a star/ascendant combination — and it notes the reading is 'general ... for reflection' rather than personalized. However, there is no explicit when-to-use/when-not guidance and no routing to panchang, festivals, or find_birth_star.

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 non-open-world, so safety is covered. The description adds genuine context beyond that: the output is hard-coded to New Delhi IST, the date must be within a year either way, and providing birth_star conditionally adds that star's tārā for the day.

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 core purpose, then the returned contents, then a compact two-clause parameter note. Dense but every clause adds information; the enumeration of limbs is long but earns its place by defining the payload.

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 covers scope, location, date bounds, and the conditional parameter. Minor omission: behavior on an invalid date or unrecognized birth_star name is not described.

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

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

Schema description coverage is 0%, so the description carries the burden and does so well: date accepts the literal 'today' or YYYY-MM-DD bounded to one year either way, and birth_star is an optional nakshatra name. Only the exact accepted nakshatra spellings are left unspecified.

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 Hindu almanac/panchang) with its geographic and timezone scope (New Delhi, IST) and enumerates the exact contents returned (five limbs, sunrise/sunset, Rahu Kaal, chaughadia, tārā). This makes it clearly distinct in substance from festivals, monthly_forecast, and find_birth_star, 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?

Usage is implied rather than stated: it tells the agent the tool is for 'a day' at New Delhi and that birth_star is optional, but gives no explicit when-to-use/when-not guidance and does not contrast itself with find_birth_star or monthly_forecast, which an agent might otherwise confuse it with.

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