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

Annotations already cover read-only/idempotent/destructive flags, but the description goes much further: local Meeus computation, no upstream call, accuracy tolerances, modeled limitations, error behavior, runtime, price, and shared free-tier limits. This is unusually rich behavioral context.

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 description is a single dense paragraph, but it is front-loaded with outputs and inputs and nearly every sentence carries operational value. The redundant 'skypeek:' prefix and pricing/rate-limit tail keep it from a 5.

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 tool with no output schema, the description explicitly lists returned values and adds accuracy, limitations, errors, latency, and cost, so an agent has enough to call it correctly. Nothing material is missing.

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 100%, and the description's parameter notes (lat, lon, optional YYYY-MM-DD date 1900–2100, IANA tz default UTC) largely duplicate the schema's own descriptions. It adds little semantic meaning beyond the schema baseline.

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 names the resource and enumerates exactly what is computed (sunrise/sunset, solar noon, day length, three twilight bands, moonrise/moonset, phase, illumination, distance), plus the input domain (point + local date + chosen time zone). It leaves no ambiguity about the tool's function, and no sibling tool computes the same quantities, even without an explicit sibling callout.

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 clearly establishes the context for use (you have coordinates, a local date, and a time zone) and gives defaults, but it does not tell the agent when to prefer it over alternatives or state exclusions. No sibling-tool routing is provided.

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