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

Goes well beyond destructiveHint=true and idempotentHint=true by disclosing the crucial asymmetry: a model change rewrites past and future reports retroactively, while a window change only applies from the day it is made. It also describes the response (before/after settings plus the arguments to restore the old values), which is the exact rollback information an agent needs before a destructive, retroactive edit.

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?

Front-loads what is being changed, then the per-field values, then the temporal consequences, then the return shape. Dense but every clause carries operative information; the parenthetical value lists are the enum documentation the schema lacks, not filler.

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?

An output schema exists, yet the description still summarizes the return as before/after settings plus restore arguments, which is the part an agent must not miss for a destructive change. Combined with the scope boundary and per-parameter constraints, nothing needed to invoke it safely is missing.

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 0% and no enums are declared, so the description carries the full burden — and does: it enumerates the three valid attribution models, restricts acquisition_lookback_days to 7/30 with its meaning (first-visit and first-open key events), and restricts other_lookback_days to 30/60/90. That is materially more than the bare integer/string schema conveys.

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 (change) and resource (GA4 property's reporting attribution model or key-event lookback windows) plus the resource path form properties/<id>. The mutation verb cleanly separates it from the read sibling ga4_get_attribution_settings without needing to name it.

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?

'Give only what changes' explicitly documents partial-update semantics, so an agent knows unspecified fields are left alone rather than reset. It also bounds scope by stating which channels may earn Google Ads conversion credit are not changed here. No explicit prerequisite (e.g., reading current settings first) or named alternative is given, so it stops short of a 5.

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