Pluto Garden

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

Annotations already declare the tool read-only, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds meaningful behavior beyond that: output degrades gracefully when time is omitted (no rising sign or houses), the server performs place lookup, and the response includes external links and guide pages. It stops short of covering accuracy caveats or error cases.

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?

Four compact sentences, front-loaded with the core capability and followed by conditional behavior, input conventions and return values. Every sentence carries information; there is no filler, though the time-conversion instruction slightly overlaps the schema.

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?

There is no output schema, and the description compensates by describing what comes back (placement details plus 3D sky link and guide pages) and how the result changes when birth time is missing. For a six-parameter open-world computation tool this is close to complete, with only minor gaps such as failure modes or place-resolution ambiguity.

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 the house-system enum and optional coordinates. The description reinforces place handling ('pass as the person said it; the server looks it up') and time conversion, but it does not explain the latitude/longitude skip-search shortcut or the house_system choice, so it adds only modest value over 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?

The description opens with a specific verb and resource ('Draw an accurate birth (natal) chart') and enumerates the exact outputs (Sun, Moon, rising sign, planets with sign/degree/house, angles, aspects). It is unambiguous what the tool produces, but it does not name or distinguish itself from the sibling tools famous_chart and sky_now, which keeps it from 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: call it when you have a birth date and optional time/place to compute a natal chart. It gives helpful input-handling guidance ('Works without a birth time', 'Pass the place as the person said it', 'Convert the time to 24-hour local time'), but it never states when to prefer this over famous_chart or sky_now, nor any exclusions.

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 the description appropriately spends its words on coverable gaps: the data-quality constraint (only self-reported birth times, with source attribution), the failure mode (missing name = unknown), and what comes back (big three, placements, source, page link). No auth or rate-limit detail, but for a read-only lookup that is minor.

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 identification of the collection, then the data constraint, then the return payload. The parenthetical example list is slightly long but earns its place by showing the event-as-name case.

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 usefully enumerates return contents (big three, placements, source, page link) and warns about the empty-result case. Complete enough to call correctly; only the sibling disambiguation 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% and the schema already documents the single name parameter with the same examples (Billie Eilish, Bitcoin). The description adds little beyond reaffirming that the name may be a person or an event, which is baseline territory.

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 (birth chart) and a specific scope (celebrities or famous moments from Pluto Garden's sourced collection), with concrete examples like Billie Eilish and the Moon landing. It does not explicitly contrast with the sibling birth_chart, so an agent must infer the difference from the 'collection' framing.

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

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

The description implies when to use it (you want a pre-sourced chart for a known public figure or event) and gives one useful exclusion — a missing name means no self-reported time exists. It never names the alternative birth_chart for user-supplied chart data, so routing between siblings 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 this as a safe, read-only, idempotent, non-destructive operation, so the description does not need to carry the safety burden. It adds useful behavioral context beyond annotations by specifying the supported date range and enumerating the astronomical data returned, including traditional full moon names and retrograde end dates.

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

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

The description is a single front-loaded sentence that immediately states the scope and then enumerates the useful outputs. It is dense but efficient, with the parenthetical 'answers is Mercury retrograde?' earning its place by grounding the tool in a common query.

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 only one optional parameter and no output schema, the description is complete enough for correct invocation: it covers the default date, supported date range, and all major returned data categories. Nothing essential for selecting or calling the tool 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 the schema already documents the optional date format, noon UTC handling, and default. The description adds meaningful constraint beyond the schema by stating the allowed range of 1901 to 2100, which helps an agent know when the parameter is valid.

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

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

The description clearly states the resource and contents: today's sky or any date from 1901 to 2100, including Moon phase, lunar dates, retrogrades, and planetary signs. It implicitly distinguishes itself from birth_chart and famous_chart by focusing on current/sky data rather than natal charts, though it does not name the 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 context is clear: use it for today's sky or historical/future dates in the 1901–2100 range, including common questions like 'is Mercury retrograde?'. It does not explicitly state when to prefer sibling tools such as birth_chart, but the context is sufficiently clear for an agent.

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