Retriever time series

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

Annotations only declare read-only/idempotent/open-world; the description goes well beyond by disclosing the auto strategy-selection heuristic (volume + window length), the sampling behavior with fidelity guarantees, that tail caveats are reported, and that pathological volume is refused with structured narrowing guidance rather than silently truncated. That is exactly the behavioral context an agent needs to set expectations on output reliability.

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 capability, then conditions, then the alternative. It is dense but nearly every clause carries information; the two long sentences are packed with nested parentheticals, which costs a little readability but not correctness.

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?

With an output schema present, return-shape explanation is unnecessary, and the description still covers the operation's mode, its fidelity caveats, its refusal behavior, and routing to the payload-fetching sibling. Nothing material is missing for correct invocation.

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%, so the schema carries the heavy lifting and baseline is 3. The description adds how the fidelity tradeoff plays out (small/moderate volume = exact counts vs high-volume = sampled) and references group-by on enrichment fields, which gives callers a reason to pick `full` vs `per_window_sampled` beyond the bare enum values.

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?

Specific verb (materialize) + resource (fidelity-aware time series) + scope (S3 archive over an arbitrary window, optional group-by). It explicitly contrasts itself with the sibling log10x_retriever_query ('actual event payloads, not aggregates'), so an agent can distinguish them without opening schemas.

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?

States two concrete when-to-use conditions (a) breakdown answers exceeding SIEM retention and (b) building baselines where grouped breakdowns live only in the archive, plus an explicit when-not with a named alternative. Nothing is left to inference.

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