get_nightly_forecast

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

With no annotations, the description carries the full burden and does it well: it discloses that deep_sky.score sorts ascending and must not be compared to telescope suitability_score (descending), that transit_alt is an estimate at scoring time rather than a solved meridian transit, and that night_window is civil darkness (-6°) not astronomical (-18°). It is silent on failure modes, however — invalid time/timezone handling, high-latitude cases where no civil darkness occurs, and whether the call has any cost — which is a real gap for a zero-annotation tool.

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 purpose, then labeled Use/Do-not-use/Requires/Interpretation/Follow-up sections that scan quickly. The closing 'Returns' block largely restates what the output schema already declares, so that section is the one part that does not fully earn its space.

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 5-parameter tool with no annotations and a rich output schema, the description covers everything an agent needs to call it correctly: when to use, when not to, required inputs, argument formats, scoring-direction pitfalls, and next-step routing. Return-value structure is correctly left to the output schema.

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 0%, so the description must compensate and it does: it documents all five parameters including the 'YYYY-MM-DD HH:MM:SS' format for time, the non-obvious caveat that a bare date means local midnight and may fall into the previous evening's night, IANA format for time_zone, and the default of 20 for limit. This is substantially richer than the bare schema types.

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 ('Get a curated list of best objects to view for the night') and immediately bounds the scope with an explicit exclusion ('not telescope-specific target matching or regional site selection'). An agent can distinguish it from get_telescope_targets, plan_stargazing_session, and get_shooting_plan without opening any schema.

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?

Uses explicit 'Use when' / 'Do not use when' clauses and names the prerequisite state ('place and night are known'). The 'Follow-up' line routes to three named siblings with the condition that selects each (known optics, imaging schedule, place/night still undecided).

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