compare_periods

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

No annotations are provided, so the description carries the full burden. It clearly discloses implementation nuances: tracker counts use current-snapshot for both periods (not historical), and only minute deltas are period-over-period. This is exactly the kind of behavioral context an agent needs to avoid misinterpretation of results. It also notes that account_id auto-resolves if omitted, which is a behavioral trait.

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 well-structured with clear sections ('Args', 'Returns', 'Implementation'). It front-loads the core purpose and output, then details parameters and caveats. Every sentence adds value, with no filler. The use of examples ('is Malick growing?') is concise and effective. Ideal length for the complexity.

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 tool has an output schema, so return format is covered there. The description provides essential usage context, parameter semantics, and behavioral caveats. The only minor gap is not mentioning potential side effects (or lack thereof), but given it's a read-only comparison, this is acceptable. Overall, it's complete for an agent to correctly select and invoke the tool.

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 explain both parameters. It does: 'days' is explained with default, cap, and rationale; 'account_id' is explained as auto-resolving if omitted. This is above the baseline of 3 for low coverage, though it could be more explicit about what account_id refers to (e.g., a specific CallRail account). Still, it adds significant meaning beyond the bare schema.

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 uses a specific verb ('Compare') and resource ('current N-day window vs the previous N-day window'), and states its output (per-company deltas, agency totals). It clearly distinguishes itself from sibling tools like 'call_summary' and 'call_timeseries' by focusing on period-over-period comparison. The examples ('is Malick growing?') add practical context.

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 concrete use cases ('catching invoice surprises before they hit') and sets expectations about the 'days' parameter (default 30, cap 365, with a hint about typo prevention). It implicitly signals when not to use (don't ask for 5-year delta), which is useful guidance. However, it doesn't explicitly name alternatives, but the guidance is sufficient.

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