RTB statistics

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description still adds behavior the annotations do not: implicit row caps (10 rows for terms groupings unless `size` is set) and the nested sub-breakdown shape produced by subdimension. It omits pagination behavior for `from`/`size` and any rate/limit notes.

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?

Three tight sentences, front-loaded with the primary scope decision (account vs. feed) before the secondary grouping behavior. The only friction is the odd phrase 'Terms groupings', which is undefined jargon and costs a little clarity without adding much length.

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?

For an 18-parameter, no-output-schema analytics tool, it covers the non-obvious axes: grouping dimension, optional feed narrowing, nested subdimension, and default row counts. Filter parameters (countries, browsers, OS, ISPs, date ranges) rely entirely on the 83%-covered schema, which is acceptable, though the date-range limits live only in schema descriptions.

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?

Adds real meaning beyond the schema: it explains that feed_id narrows to a single feed, that subdimension must differ from group_by and injects a nested `sub` block into each row, and that `feed` splits rows per RTB feed. These semantics for subdimension/group_by interaction are not derivable from the enum lists alone.

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+resource (RTB statistics) and precise scope: account-wide, or narrowed to a single feed when feed_id is given. Clearly distinct from sibling readers like get_rtb_feed (single feed details) and get_balance_stats (different metric family), so an agent can select it without opening the 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?

It conveys scope conditions (whole account vs. one feed via feed_id, terms groupings default to 10 rows), which implies usage context, but never says when to prefer this over alternatives such as get_order_stats, get_rtb_feed, or list_rtb_feeds. No explicit when-not or alternative routing is provided.

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