get_multiday_stargazing_plan

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

With no annotations, the description carries the full burden and does so thoroughly: it flags that recommendation_score is a relative ranking rather than a threshold, that _meta.status=success can still carry per-night errors/warnings, that missing night-hour coverage means unknown rather than clear, and that civil darkness (-6°) is not astronomical darkness (-18°). These are non-obvious interpretation traps an agent would otherwise get wrong.

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?

The label-based structure (Use when / Do not use when / Requires / Returns / Follow-up) is well front-loaded and each sentence carries distinct information. The Returns block is dense but every clause is a caveat that prevents misreading; only minor tightening is possible.

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, yet the description still usefully summarizes the shape (data.query, per-night plans, best night, summary) and the caveats around it. Requirements, scope limits and follow-up routing are all covered; the only real gap is the unexplained optional tuning parameters.

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 0% across 19 parameters, yet the description only explains the four bbox bounds, start_date, time_zone and an optional night count. Twelve tuning parameters — network_type, target_limit, max_locations, road_radius_km, candidate_limit, min_height_diff, weather_provider, observation_style, avoid_popular_spots, popularity_radius_km, prefer_quiet_at_night, db_config_path — receive no semantic explanation anywhere, so the agent must guess their effect and valid ranges.

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 pair and resource: 'Compare one to seven consecutive nights and recommend the best night and place.' It also names the sibling tools it would be confused with (plan_stargazing_session, get_best_stargazing_plan) and what each is for, so an agent can disambiguate without opening schemas.

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?

Explicit 'Use when' / 'Do not use when' blocks list the positive trigger (an existing bbox-first integration, 1-7 consecutive nights) and the exclusions (new intent-based integration, nonconsecutive dates, >7 nights, background task status). Alternatives are named in the Follow-up line.

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