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

Annotations already establish that this is a safe, idempotent read (readOnlyHint=true, destructiveHint=false, idempotentHint=true), so the description does not need to cover mutation semantics. It usefully goes beyond annotations by clarifying the output semantics — ColumnName is the lower-case source name and Total/Value are per-source rather than survey-wide — which is exactly the kind of disambiguation that prevents misreading the result.

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 tight sentences with no waste. The purpose is front-loaded and the clarifying note about column/per-source semantics follows immediately.

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?

With an output schema present and annotations covering the safety profile, the description need not explain return structure, yet it helpfully disambiguates the column meanings. The only gap is the absence of any routing guidance toward the by_date/by_device/counts siblings, which an agent with several near-identical tools would benefit from.

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%, with the single 'code' parameter fully documented as the 8-character publication code returned by list_surveys. The description adds no parameter-level detail, so the schema carries this dimension entirely; baseline 3 applies.

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 states a specific verb+resource ('Returns response counts') and a clear grouping dimension ('grouped by traffic source'), which distinguishes it from the by_date, by_device, and overall counts siblings. It stops short of naming those siblings explicitly, so the differentiation is inferable rather than spelled out.

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 grouping-by-source framing implies when this tool is appropriate (per-channel analysis) versus the survey-wide or by-date variants, but there is no explicit when-to-use or when-not-to-use guidance and no named alternative. Usage is left to inference from the tool name and grouping clause.

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