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

Annotations only cover the safety profile (readOnly/idempotent/non-destructive), and the description adds substantially beyond that: defaults (no from/to = last 3 days, no resolution = all raw points), the MAX_RANGE_POINTS truncation and how to detect it from a lower-than-expected count, the response payload shape, geo-sensor lat/lng vs null value_*, and UTC on both input and output. That is exactly the context annotations cannot supply.

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, then defaults, then response shape, then failure mode, then timezone caveat — a sensible order. Slight redundancy: UTC is stated twice and "Rein lesend" restates the readOnly annotation, and the bilingual keyword tail is padding, though useful for matching.

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?

No output schema exists, and the description fully covers the return object ({count, resolution, points[...]}) plus the geo-sensor special case and the truncation failure mode. An agent has everything needed to call it correctly and interpret the result without further lookup.

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 baseline is 3, but the description adds operational meaning: resolution as a raw-vs-grid tradeoff with a 60s floor, the 300s heuristic for a daily route, and the consequence of omitting from/to. Much of this echoes the schema text, so it is incremental rather than fully compensating.

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?

Front-loads a specific verb+resource in caps ("VERLAUF einer Zeitreihe lesen") and pins the scope to points between two timestamps. It then names the intent it serves (course, daily route, measurement curve), which distinguishes it from the sibling onto_series_last that would return only the latest value.

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 concrete when-to-use framing plus prerequisite routing: object_udid and series_key are mandatory and come from onto_object_show's series_keys. It also advises choosing resolution by use case (300 for a daily route). It stops short of an explicit exclusion clause naming onto_series_last for single latest values, so a routing decision is left implicit rather than stated.

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