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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorld, so the safety profile is covered. The description adds a genuinely useful behavioral note—that results include incomparability warnings—which an agent would not otherwise know. It stops short of describing the response shape, limits, or what triggers the warnings.

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?

A single compact sentence with the core operation front-loaded and no filler. It is efficient, though the terseness contributes to the missing mode and usage detail rather than compensating for it.

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, 4 parameters, and the mode enum undescribed, the description should carry more weight than one sentence. It omits how mode interacts with the date defaults and what the incomparability warnings look like, leaving real gaps for an agent configuring a comparison.

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 50%, and the one undocumented parameter is the critical one: `mode` has an enum of previous_period/previous_month/previous_year but no description in the schema and no explanation here. The phrase 'the previous one' is ambiguous precisely where mode needs disambiguation; only date_from/date_to are documented, and that documentation lives in the schema, not the description.

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 operation (comparison of a period with the previous one) and names the outputs (absolute/relative change, incomparability warnings). This is distinguishable from sibling analytics tools like get_performance or find_anomalies, though the description never explicitly contrasts with them or clarifies what 'the previous one' means against the three available modes.

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?

There is no guidance on when to choose this tool over get_performance, find_anomalies, or find_waste, which all touch related analytics territory. No prerequisites, exclusions, or alternative routing are mentioned.

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