compare_periods

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

With no annotations, the description carries the full burden and does useful work: it discloses the returned statistics (mean/median/n, delta %, Cohen's d, plain verdict) and the default exclusion of travel days. What it never states is that this is a read-only, side-effect-free operation, nor whether the comparison itself has any prerequisites such as ingested data or configured periods.

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?

Three dense sentences, front-loaded with the core action and with no filler. The parenthetical about period_a/period_b becoming labels is slightly compressed and requires a second read, but every sentence carries information an agent needs.

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?

The description substitutes well for the absent output schema by enumerating return values, and it explains default behavior. However, for a six-parameter tool with zero schema documentation, omitting the metrics filter and never saying what valid period names look like leaves the definition only minimally sufficient.

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 0%, so the description must compensate, and it does for most inputs: a_range/b_range get an explicit format example ('2025-03-01..2025-03-31'), period_a/period_b are explained as labels in ad hoc mode, and the default of the first two named periods is given. The metrics parameter is never mentioned at all, leaving one of six inputs entirely undocumented, and the travel-day note is not tied to the home_only flag by name.

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 first sentence names a specific verb and resource (compare two periods) and the rest clarifies how periods are selected. It references set_periods as the source of named periods, which helps position it among siblings, but it does not distinguish itself from monthly_trends or rolling_baseline, which are plausible alternatives for time-based comparison.

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?

It clearly lays out the two invocation modes — named periods from set_periods (with the default being the first two) or ad hoc ranges — which is exactly the decision an agent must make before calling. It stops short of saying when this tool should be preferred over monthly_trends or rolling_baseline, so there is no true alternative routing.

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