JPL small-body mission design

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower. The description adds real context: object mode returns pre-computed stored options rather than computing on demand, list mode is ranked by crit, and two API modes are deliberately unexposed. It does not discuss rate limits or result-size behavior for list mode.

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 API identity, then mode behavior, then explicit exclusions. No filler and nothing repeated from the schema verbatim.

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 13-parameter, zero-required, read-only tool with no output schema, the description covers the mode selection that the flat schema cannot express and rules out two unimplemented modes. Return contents are named for object mode but list-mode record fields (other than crit ranking) are left implicit, which 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 coverage is 100%, so every parameter is already documented in the schema, making 3 the baseline. The description reinforces the mode split (which params belong to object vs list mode) and notes that JPL defaults year to the next five years, but it does not clarify the mutually exclusive nature of des/spk/sstr or how list-mode filters combine.

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: ballistic mission options to asteroids and comets from the JPL Small-Body Mission Design API, then enumerates its two operating modes (object vs list). An agent can tell what it returns (launch/arrival dates, V-infinity, time of flight) without opening the schema. It never names a sibling tool, so it is clear but not explicitly differentiated from jpl_scout or jpl_horizons.

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?

Clear routing logic: use object mode (des/spk/sstr) for one stored object and list mode for ranked accessible bodies by launch year. It explicitly rules out unsupported work by stating porkchop maps (mode M) and mission-extension searches (mode T) are not exposed, which prevents wasted calls. No guidance on when to prefer this over the neighboring mission/accessibility siblings.

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