Set the attribution lookback window (1 to 90 days)

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

Annotations only say readOnlyHint=false, idempotentHint=true, openWorldHint=true. The description adds genuinely useful behavior: the call is a no-op unless confirm:true, and there is no server-side dry run, so the confirmation gate is purely client-side. That's context an agent cannot derive from the annotations alone.

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?

Two short sentences with the operation front-loaded and the execution gate immediately after; nothing extraneous. The day range is duplicated from the title, a minor redundancy but not harmful.

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 single-setting write with no output schema, the definition covers the mutation, the range, the endpoint, and the confirmation requirement. What a preview response actually contains is left to the confirm parameter description, which is acceptable.

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 67%, and the two optional parameters (confirm, idempotencyKey) already carry their own descriptions. The description's only parameter-level addition is the 1-90 range, which the schema already enforces via minimum/maximum, so it mostly restates structured data.

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 verb and resource ('Set the attribution lookback window') with the valid range and the underlying endpoint (PUT /v1/tracking/settings). The get/set pairing with sibling tracking_getSettings is inferable but never named explicitly.

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 makes clear that calling without confirm returns a preview rather than mutating state, which implies the intended two-step flow. It does not, however, explicitly contrast this with tracking_getSettings for reading the current value or state when a change is warranted.

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