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

Annotations already provide readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavior beyond that: the forecast is grounded in stockout-repaired history, recovery is inventory-gated, first month anchors to actual MTD, and the engine runs nightly. This is strong context, though it doesn't fully elaborate on pagination mechanics or output size.

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 and information-rich, with the core subject front-loaded. Each sentence adds a distinct fact: content, grounding, currency, pagination, and usage caveats. The ALL-CAPS emphasis and slightly breathless pace reduce scannability slightly, but no sentence is wasted.

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 report with no output schema and nullable parameters, the description covers the essentials: what data is returned, how it is computed, how to paginate, how to scope currency, and what caveats to quote. The only notable gap is the exact shape/format of diagnostics.trend_check and quote_rules, but the description does enough to let an agent call 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 coverage is only 25%, so the description carries most of the burden. It adds meaning for currency ('One currency per call (EUR spans the EU marketplaces)') and for offset/limit ('Page rows via offset/next_offset'). It does not explicitly explain limit/offset defaults or constraints, but it meaningfully compensates for the sparse 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 opens with a specific resource: 'THE 12-month per-ASIN unit forecast (nightly engine)' and enumerates its contents: brand totals vs last year, seasonality index, diagnostics including trend_check, per-ASIN rows with inventory gate fields, and LOW STOCK flags. This clearly distinguishes it from siblings like forecast_reorder_report and data_query.

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?

Provides explicit usage directives: 'One currency per call (EUR spans the EU marketplaces)', 'Page rows via offset/next_offset', 'Monthly grain also queryable via data_query dataset forecast', and 'ALWAYS surface diagnostics.trend_check and quote_rules caveats when quoting numbers.' These are actionable when-to-use and how-to-use instructions, including an alternative path.

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