get_lightcurve

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

With no annotations, the description carries the full behavioral burden, and it does disclose two genuinely useful behaviors: bin_days aggregation is by median, and long series are automatically downsampled to max_points. It says nothing about return format (columns, uncertainties), ordering, or what happens when the series is unknown or empty, which are important for a data-retrieval tool with no output schema.

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?

Two dense sentences with no filler, and the core concept plus identifier examples are front-loaded. The terseness costs a little clarity, but nothing is wasted.

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 6-parameter tool with zero schema description coverage, no annotations, and no output schema, the description leaves the required 'case' argument, the return shape, and the fallback behavior undocumented. It covers roughly half of what an agent needs to call this 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 0%, so the description must compensate, and it partially does: it gives concrete series identifier syntax and explains bin_days and max_points semantics. However, the required 'case' parameter is never mentioned, nor are the accepted start/end formats (the schema allows number or string) or the meaning of bin_days=0.

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 is a noun phrase, "Points of one series," rather than an explicit verb+resource statement, though the series examples ('NEOWISE:W1', 'AAVSO:V') make the domain clear. It never distinguishes this fetch from nearby siblings such as describe_series, compare_windows, or fold, so an agent must infer that this is the raw photometry point retrieval.

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?

It mentions that the time window and binning are optional but gives no condition for when to use this tool versus alternatives, nor any prerequisite (e.g. whether the series must be registered to the case first). Usage must be guessed entirely from the name.

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