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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes further by disclosing the required permission (send_planner.view), the 548-day ceiling, the 90-day default window, and the provenance caveat that figures are estimated from daily per-node stock rather than the marketplace promise. It does not describe response shape beyond content, but with no output schema and rich annotations this is a strong addition.

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 core definition is front-loaded in the first clause, and every sentence carries content. The second sentence is dense, stacking the range cap, default, and permission requirement into one string, which is efficient but slightly overloaded.

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 7 optional-leaning parameters, no output schema, and a moderate analytical surface, the description covers the essentials: what is measured, the window bounds and default, data provenance, and the permission gate. Remaining gaps (how product_id relates to sku, exact response granularity) are minor and largely covered by the schema.

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 already 86%, so the baseline is 3; the description still adds real meaning by clarifying that omitting SKU yields the whole network and by pinning down the date-window semantics ('up to 548 days; defaults to the last 90'). It does not clarify how product_id, destination_warehouse_id, or send_plan_id interact, but the schema documents those.

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?

Names a specific metric (estimated 2-day reach over time), the entity scope (one SKU or the whole network), and the unit of measure (weekly % of buyers within ground reach of an FC/warehouse holding sellable stock). An agent can distinguish this from siblings like get_send_plan or explain_inventory_gap without opening the 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?

Usage is only implied by the description of what is returned (a historical trend, not a point-in-time snapshot). The clause 'not the marketplace delivery promise' disambiguates the data source but not tool selection. There is no explicit when-to-use, when-not-to-use, or named alternative sibling.

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