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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is handled. The description adds output-content transparency (old values, new values, timestamps) but discloses no behavioral limits such as how 'recent' is defined, default time windows, or whether history coverage is restricted. 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?

Two sentences with no filler: the first front-loads the action and return contract, the second adds filter-relevant coverage. Every clause earns its place and provides information beyond the title.

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?

Moderate-to-high complexity (9 optional parameters, no output schema, no enums, no required fields) with no defaults explained. The description conveys the core return concept but not how period_days interacts with start_date/end_date, what the default time window is, or how next_offset pagination behaves. Sufficient for a basic call, gappy for a precise one.

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 covers 5 of 9 parameters (56%); the description partially compensates by enumerating covered change types (bid, budget, status), which hints at values for field/change_type. However, start_date, end_date, period_days, and campaign_name_contains receive no meaning in either the schema or the description, leaving date-window semantics unexplained for a history tool.

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 ('Get') and resource ('recent campaign change history'), and specifies the return contract ('what changed, when, old values, and new values'). The history-with-old/new-values semantics clearly distinguish it from current-state siblings like ppc_campaign_details and ppc_campaign_metadata, even without naming them.

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 use case (auditing what changed in campaigns) is implied by the wording, but there is no explicit when-to-use guidance, no exclusions, and no named alternatives. In a sibling set of roughly 90 tools, an agent gets no routing help beyond the implicit history-vs-state distinction.

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