scan_planetary_aspects

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description adds real substance: Swiss Ephemeris tropical geocentric apparent basis, mean nodes as default, bracketed-root solving with relative-speed station splits, server-side checks before results return, and query-local (non-universal) cycle IDs. This is well beyond annotation coverage; only the response shape/pagination remains implicit.

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 scope and semantics, which is good, but the prose is dense run-on text mixing mechanics, cycle-ID caveats, verification workflow, and result-shaping options. Roughly a third of the words are the verify_calculation_claims protocol, which crowds out parameter detail the schema doesn't supply.

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 an 11-parameter, multi-mode tool with no output schema and 18% schema coverage, the description covers mechanics, precision options, and result shaping, but not output field names (only 'windows', 'year_summary' appear in the include schema), body-name vocabulary, or date string formats. An agent could call it but would be guessing on inputs and re-reading results.

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 only 18%, so the description must carry the load, and it explains mode, orb_deg ('separate from exact'), output_precision values, timezone_name as an optional IANA zone, detail_level=summary vs include, and the [0,180] aspect angle bound. But the four required parameters are essentially untouched: planet_a/planet_b naming is only 'arbitrary supported body pair' with no enumerations, and start_date/end_date format is never stated. That leaves the most critical inputs underspecified.

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?

Names a specific verb and resource ('Scan exact planetary aspects') and pins the scope tightly: UTC inclusive ranges, years 1800–2399, 200-year cap. It never names a sibling such as calculate_aspect_windows or calculate_transits_to_natal, so the agent can describe the tool but must infer which of several aspect/window tools to pick.

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?

Offers mode-level guidance implicitly ('mode=orb_window returns clipped entry/exit windows plus exact events') and a mandatory downstream step: call verify_calculation_claims before interpreting results. However it never states when to prefer this over the many sibling calculation tools, nor any prerequisites or exclusions beyond the date bounds.

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