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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavior: the omit/pass fieldName dual mode, bounded categorical results with an other_event_count catch-all, and that nested structures come back as dynamic JSON rather than a fixed DTO. It does not say what happens for an unknown fieldName or invalid eventName, so it falls short of 5.

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?

Five sentences, each carrying a distinct fact (mode 1, mode 2, data shape caveat, performance_sample special case, upstream source and exclusion). Front-loaded with the primary behavior and free of restatement of the name or annotations.

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?

A read-only, non-destructive tool with no output schema and full parameter coverage; the description conveys both call modes, the result shape, and the upstream discovery path, which is enough to invoke it correctly. Minor gaps remain around failure/empty cases and how many categorical values 'bounded' means.

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 100%, so the baseline is 3, but the description genuinely adds semantics beyond the schema: fieldName is optional and its presence/absence selects two different result shapes, and nested JSON stays inside that field's value. It adds nothing further about eventKind/applicationId beyond what the schema text already states.

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 resource and scope ('Preaggregated detail for one event') and then says exactly what the tool returns in each mode: field inventory with type/coverage/cardinality/summary, or bounded top categorical values plus other_event_count. An agent can distinguish this from the sibling telemetry tools (session_facts, timeseries, analytics) 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?

Explicit two-step workflow ('Call without fieldName... Call again with one fieldName'), an explicit upstream dependency ('Use event names discovered in get_game_telemetry_analytics'), an explicit exclusion ('do not request raw events'), and a named special case (performance_sample FPS/frame-time/stutter). Nothing is left to inference.

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