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

Annotations already cover read-only/idempotent/non-destructive, and the description adds substantial context beyond them: the 1 MiB cap, that data travels over the network to a hosted server, which errors are recoverable and how, and an explicit list of what is NOT inferred (calibrated coverage, causal explanation, path/peak probability). That is a rich, honest behavioral profile.

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 the core operation and no filler sentences; each clause conveys substantive scope or limit information. However, it is a long unbroken block of semicolon-separated caveats with no structural grouping, which makes it slower to scan than a 3-parameter readback tool warrants.

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 a nested artifact object, three parameters, and an output schema, the description covers invocation, input limits, error handling, and expectation boundaries. Even though the output schema exists, the added framing on what the result does and does not mean prevents misreading medians as intervals.

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 100%, so the schema documents artifact, series_index and variate_index in detail; per the rubric the baseline is 3. The description adds marginally beyond that — the 'pass {artifact: <forecast result artifact>}' example and the version/shape error-recovery note — but repeats the 1 MiB and multi-series guidance already in the schema.

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+resource (deterministic calculations over a saved ephemeris.forecast v1 artifact) and the framing 'No inference or forecast charge' cleanly separates it from the sibling `forecast` tool that generates artifacts. An agent can tell it is a readback/describe operation, not a compute operation, without opening the 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?

Gives a concrete invocation example plus selection guidance for series_index/variate_index when multiple results exist, and a clear failure path ('fixing the artifact or using CLI, never rerunning inference'). It does not explicitly state when to prefer it over `forecast`/`plot_forecast`, but the context is unambiguous.

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