observe_tonight

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

Annotations already establish read-only/idempotent/open-world, so the description's added value is in the observability logic: Sun below -12 deg, min altitude, min moon separation, and the ranking rule (brighter, younger, longer window). This lets the agent predict both filtering and ordering. It does not mention rate limits, empty-result behavior, or cost of the computation.

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?

Dense and front-loaded: the core purpose and filter chain come first, then the use case, then the return shape. Slightly long with a parenthetical return-summary, but nearly every clause carries filter or output meaning. No filler sentences.

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 9-parameter, open-world query with a rich return payload, the description covers observability criteria, ranking, and the key returned fields (night window, Moon illumination, max altitude, transit, observing window, TNS link); an output schema is also present. The gap is modest: `limit` and `include_classified` semantics remain undocumented and there is no note on what happens when no targets match.

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 carry the load, and it covers most parameters: lat/lon units and sign convention, date format and default, max_age_days, mag_limit (explicitly TNS discovery magnitude), min_altitude, and min_moon_sep. Only `limit` and `include_classified` are left unexplained, keeping it just below a 5 given the zero schema coverage.

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?

Opens with a specific verb-like framing ('What to observe tonight:') followed by a precisely scoped resource: recent, bright, still-UNCLASSIFIED TNS transients observable from a given site and night. The filter criteria are spelled out inline, so an agent can distinguish this from tns_search, rubin_recent, or whats_here 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?

Explicitly states the intended use case ('plan follow-up photometry or spectroscopic classification') and defines the date semantics ('local evening of `date`, default today UTC'). It does not name exclusion cases or an alternative sibling for when a stricter/looser search is wanted, so it stops short of a 5.

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