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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioral value by enumerating the returned point fields (value, change, change_percentage, yoy_change, yoy_change_percentage, compared_period) even though no output schema exists, and by stating that MoM and YoY are precomputed. It also warns against manual aggregation with granularity. Minor gaps remain: no note on ordering of points or what happens for an unknown metric name.

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 purpose, then alternatives, then time-range semantics — the right order for an agent scanning quickly. The dense parenthetical field list and the 'not a period list like other tools' remark repeated from the schema cost some efficiency, but nearly every sentence carries decision-relevant information.

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 no output schema, the description correctly compensates by listing the per-point return fields, and it covers metric selection, time-range options, and granularity. For a five-parameter read-only tool with full schema coverage, the only missing pieces are edge behavior (invalid metric, empty range) and point ordering.

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 already documents every parameter including the periods/date_from/date_to alternatives and granularity guidance. The description largely restates this ('periods is a COUNT, default 12', 'date_from/date_to — not a period list'), adding only the cross-tool clarification that other tools take period lists. That is marginal added meaning over a fully documented schema, so baseline applies.

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: a time series for a SINGLE named metric, with the exact metric families enumerated (buckets, derived P&L aggregates, tenant_config.pnl_labels categories). It also names what it is not (not all-metrics-per-period, not grouped sums), so an agent can distinguish it from get_periodic_summaries and compute_aggregates without opening either 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?

Explicit routing rules: 'Prefer get_periodic_summaries instead when you need ALL metrics for a period at once' and 'prefer compute_aggregates instead for account/cost-center/category SUMS with grouping, share, or cumulative', including the important caveat that compute_aggregates cannot compute the derived aggregates this tool knows about. Usage is conditioned on both question shape ('how does X develop over time') and metric type.

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