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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds meaningful behavioral context beyond that: 'fresh' data, 'exactly one source,' the non-ranking nature of site-derived ideas, and the USD convention for keyword-research estimates. It also clarifies that paid competition is not organic difficulty, preventing a common misinterpretation.

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 long but information-dense, and every sentence carries a real constraint or routing rule. It front-loads the core invariant ('fresh, read-only table from exactly one source') before diving into source-specific guidance, and the caveats about keyword research are essential rather than 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?

Given the tool's complexity—six distinct data sources, nuanced keyword-research semantics, and a free-form request parameter—the description is remarkably complete. It covers source selection, request construction, row limits, combining results via transform, and the key pitfalls, while the presence of an output schema makes a return-format explanation unnecessary.

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 baseline is 3, but the description adds substantial meaning for the `source` and `request` parameters. It explains what each source is for, what a self-contained request must include (scope, dates, metrics, dimensions, filters, ordering), and adds constraints like at most 25 rows when no count is requested.

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 opens with a precise action statement: 'Use for one fresh, read-only table from exactly one source,' naming the resource class and its scope. It then enumerates each source (google_ads, meta_ads, etc.) with the exact use case it serves, making the tool's purpose unmistakable and differentiated from the sibling tools.

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 gives explicit when-to-use guidance by mapping each source enum to a specific reporting need, then says to use additional fetch_data calls for other sources and transform artifacts when combining. It also provides hard rules such as requiring an explicit market and language for keyword research, never inferring them, and capping unrequested keyword rows at 25.

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