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), yet the description adds substantive traits: preaggregated and pseudonymized data, dynamic sanitized JSON in ordered chunks, deliberate exclusion of repetitive event types, and the caveat that facts are not a complete user history. None of that is derivable from the annotations or schema.

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 tightly packed sentences, front-loaded with the resource and its purpose, then constraints, then exclusions. Every sentence carries a distinct, actionable fact; nothing is restated from the schema or title.

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 no output schema, the description still characterizes the return payload (sanitized JSON in ordered chunks, paginated, cursor-driven) and warns about its limits as a history source. Combined with the missing-parameter constraint and exclusions, an agent has everything needed to call it correctly and interpret results.

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 a genuine cross-parameter constraint absent from the schema: at least one of eventName, fieldName, sessionRef or userRef must be supplied (the schema only marks applicationId/dateFrom/dateTo as required). It also sets the paging expectation ('default 20-session page'), which only partially duplicates the schema's limit default.

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?

Names a specific resource ('paginated, preaggregated and pseudonymized session facts') and a concrete query class (sequence questions like item-before-death or restart-after-defeat). It implicitly separates itself from the raw-event sibling by stating 'they are not raw events', so an agent can distinguish it from get_game_telemetry_analytics/timeseries 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?

Gives clear when-to-use (sequence questions), explicit when-not ('never filter session facts by core_ping or performance_sample', 'not for per-session FPS analysis'), and a pagination policy. It stops short of naming the sibling tool to use instead for those excluded cases, so the alternative is implied rather than stated.

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