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 goes well beyond that by disclosing the billing model (0.1 credit per call, billed in blocks of 10, only successful calls charged), sandbox-key behavior (free, fixed sample), and a determinism guarantee. It also notes that a zone-less datetime is refused with invalid_datetime — a failure mode an agent needs to avoid. This is exactly the kind of context annotations cannot express.

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?

Purpose is front-loaded in the first sentence, followed by return fields, cost, determinism and a concrete example — a sensible ordering with no filler. It is on the dense side, packing four distinct concerns into one block, but every sentence carries information an agent would otherwise have to guess.

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 structure need not be re-explained, yet the description still previews the fields usefully. Combined with cost, determinism, sandbox behavior, the invalid_datetime edge case and a full example call, an agent has everything needed to invoke this correctly on the first attempt.

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 baseline is 3, but the description adds real meaning: it explains what `equatorial: true` actually yields (apparent right ascension and declination), notes that nakṣatra/pada appear only when sidereal, and supplies a worked argument set showing bodies, zodiac and ayanamsa combined. That is useful semantics beyond the schema text rather than a repetition of it.

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 — 'Sun, Moon, planets and lunar nodes at one moment' with the exact returned quantities (longitude, latitude, distance, speed, retrograde flag, sign, nakṣatra/pada, optional RA/dec). An agent knows precisely what this returns, and the title 'Positions at a moment' reinforces it. It does not, however, differentiate itself from near-name siblings like get_ephemeris_angles or get_ephemeris_series, which a reader must infer from the sibling names 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 or when-not-to-use statement, and no sibling alternative is named despite four other get_ephemeris_* tools in the list. The cost/determinism lines help an agent decide whether to spend a credit, but they are operational facts, not routing guidance. Usage is only weakly implied by the example arguments.

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