Historical time series

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context: oldest-first ordering, limit truncation from the oldest end, default windows, max windows per metric type, metric/zone availability constraints, and sample mode behavior. Minor gap: no explicit note about error cases or rate limits beyond the free key limit.

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 dense but well organized: it front-loads the core behavior, then ordering/pagination, then metric specifics, then authentication. It is on the longer side, but every sentence adds information that affects how the agent calls the tool; no filler or tautology.

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 read-only time-series tool, the description covers the critical decision space: metric availability, zone restrictions, time windows, pagination, authentication, and sample-mode behavior. There is no output schema, so a few return-format details (e.g., exact row structure) are left implicit, but the provided context is strong enough for an agent to select and invoke the tool 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 description coverage is 100%, so the schema already documents all parameters and defaults. The description adds meaningful semantics beyond that: which metrics are available in which zones, how limit truncates from the oldest end, and how start/end should be used for pagination. This goes beyond simple field-name repetition.

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 clearly states what the tool does: returns time series for one metric in one zone over a start/end window. It distinguishes itself from siblings by explicitly mentioning get_latest and get_zone_brief for current values, and it also specifies ordering semantics.

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?

The description provides explicit guidance on when to use this tool vs alternatives: use get_latest or get_zone_brief for current values, set start close to now for latest N points, paginate with start/end for longer windows, and mentions authentication modes. It gives concrete scenarios and constraints.

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