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

Annotations already mark the tool as read-only, idempotent, and non-destructive; the description adds valuable behavior beyond that: missing connections are named rather than silently returning empty data, GA4 cannot attribute AI traffic so it files it as 'Direct', and the tool reads connected/stored data without consuming AI credits. No contradiction with annotations.

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 but front-loaded with the core purpose and then expands into distinctions, alternatives, and cost. Each sentence carries useful information, though the long enumeration of action groups could have been tightened without losing meaning.

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?

The description covers purpose, scoping, measurement differences, missing-connection behavior, AI engagement attribution, and cost, and an output schema exists. The main gap is the mismatch between described actions and the actual action enum containing only ai_pages, which leaves an agent uncertain about whether other described actions are callable.

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 100%, so the parameters are already well documented. The description adds useful action-level semantics, notably that GA4 actions and Ads actions target different systems, but it does not explain days or limit in more depth. Given the baseline of 3 for full schema coverage, this is adequate.

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 clearly states the tool's purpose: GA4 traffic and Google Ads account/campaign/search-term performance, plus first-party AI engagement. It also differentiates from gsc_performance by noting Search Console clicks are measured separately. However, it references action names like overview/sources/landing_pages/top_pages and ads_* that are not present in the action enum, which slightly blurs what the tool can actually execute.

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 alternative routing: 'for search clicks use gsc_performance'. It also clarifies GA4 vs Search Console measurement semantics, states the tool is pre-scoped so no domain/site parameter is needed, and explains how missing connections behave instead of returning empty data. This gives an agent enough context to decide when to call this tool versus its siblings.

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