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

Annotations already cover read-only/idempotent/closed-world, and the description goes well beyond them: deterministic JPL DE440 computation with no LLM, retrograde passes included, a per-result meta.result_sha256, the pricing model, and the free-call allowance. This is exactly the extra behavioral context annotations cannot carry.

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 dense, front-loaded sentences: mode definitions come first, then determinism/provenance, then the pricing/invocation detail. No sentence is filler, and the two modes are the leading structure.

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 nested four-parameter tool with no output schema, the description covers what matters: what each mode returns (per-planet natal house; exact perfection minute), the window bound, provenance via hash, and cost/access. 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 coverage is 75%, so the schema does much of the work, but the description adds real meaning: the 366-day / 62-day-with-Moon window bound and the guarantee that exact UTC minute hits, including retrograde passes, are returned. It does not explain the options object or the natal fields, which the schema already documents.

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 verb+resource (compute transits to a natal chart) and clearly splits the tool into two modes, 'transit' (aspects at one moment) and 'window' (exact perfection times). It is precise about scope, but it never distinguishes itself from siblings like 'aspects', 'synastry' or 'natal_chart', which an agent could easily confuse with 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 mode selection is explained by argument ('transit' vs 'window'), and the window limits (366 days, 62 with the Moon) tell the agent when the window mode is viable. There is no explicit when-not guidance or naming of an alternative sibling tool, so it stops short of the top score.

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