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

Annotations already declare read-only, idempotent, non-destructive. The description adds real context beyond that: a hard 30-day lookback cap and a detailed enumeration of returned fields (user_email, client_type, operation, changed fields, old→new values). It does not discuss auth or pagination, but for a read-only tool this is solid added value.

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 the platform scope and verb, then params, then routing in a single dense paragraph. The caps for emphasis are readable, though the long inline field enumeration is slightly heavy; every clause still carries information.

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?

Given an output schema exists, return-value description is bonus rather than required, and the description goes beyond by enumerating fields. It covers purpose, routing, a key constraint, and most params; the only gap is the undocumented limit parameter, which is minor.

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 0%, so the description must compensate, and it does for three of five params: days (max 30), resource_type (with concrete examples like CAMPAIGN/AD_GROUP), and operation (CREATE|UPDATE|REMOVE valid values). It omits any mention of limit or customer_id, leaving two params undocumented.

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 (lists), resource (Google Ads account changes), temporal scope (last N days), and the returned fields. It explicitly scopes to 'GOOGLE ADS ONLY' and names the sibling meta_change_history, so an agent can distinguish it from related audit tools without opening any 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?

Names meta_change_history as the alternative for the Meta audit trail, which routes the agent correctly. It does not mention tiktok_change_history (also a sibling), so sibling coverage is incomplete, but the when-to-use framing is clear.

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