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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still adds real behavioral context beyond them: pseudonymization, preaggregation, dynamic sanitized JSON in ordered chunks, intentional exclusion of repetitive events, and a warning that results are not a complete user history. That said, it says nothing about ordering guarantees or cursor lifetime, leaving some behavioral surface undocumented.

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?

Purpose and the required-filter rule are front-loaded, and each remaining sentence adds a distinct constraint (pagination, non-completeness, excluded events). It is dense rather than bloated, though the illustrative example clause and the two-part exclusion sentence could be tightened slightly.

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 9 parameters and no output schema, the description carries the return-value burden and does so adequately ('dynamic sanitized JSON in ordered chunks', pagination via cursor). The main residual gap is that it never states what identifying fields come back (sessionRef/userRef, which the schema only implies as outputs) or ordering semantics.

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?

With 100% schema coverage the baseline is 3, but the description adds a cross-parameter constraint the schema does not express at all: at least one of eventName, fieldName, sessionRef or userRef must be supplied. It also reinforces the pagination contract ('default 20-session page', fetch next page only when needed) that maps to limit/cursor.

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 names the specific resource ('paginated, preaggregated and pseudonymized session facts') and the class of question it answers ('whether a player found an item before dying or restarted after defeat'). It also draws a hard boundary against neighboring capabilities by stating these are 'not raw events' and explicitly not for 'per-session FPS analysis', so an agent can separate it from the analytics/timeseries siblings without opening schemas.

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 gives explicit preconditions ('At least one of eventName, fieldName, sessionRef or userRef is required'), an operating procedure ('Start with the default 20-session page and fetch another page only when the current question needs it'), and hard exclusions ('never filter session facts by either name' for core_ping/performance_sample). Both when-to-use and when-not-to-use are stated rather than inferred.

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