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

Annotations already declare the safe read-only/idempotent profile, but the description adds substantial context beyond them: the 31-day max span, the 50-default/100-capped inventory, cursor-following rules to avoid over-fetching, dynamic JSON with possible unknown fields, and the critical 'missing or null never means zero' semantics. It also flags the response as evidence rather than a conclusion, which is meaningful behavioral framing.

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?

The purpose is front-loaded in the first sentence and every subsequent sentence carries a distinct constraint rather than filler. It is dense and slightly long, but no sentence is redundant, so it earns most of its 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?

With no output schema, the description takes on the burden of describing returns and does so concretely (volume, inventory, sessions, users, duration, freshness, plus schema_version/period/sample sizes to inspect). Combined with the pagination and date-range rules, an agent has everything needed to call and interpret the tool correctly.

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%, establishing a baseline of 3, but the description adds real meaning: dateFrom/dateTo are inclusive calendar dates that may span at most 31 days (a constraint absent from the schema), and eventCursor should only be followed when more event types are needed for the current question. This is value beyond the schema, though eventLimit's stated bounds largely duplicate the schema.

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 and resource ('compact overview of one game's preaggregated telemetry') and immediately enumerates what it covers (volume, event inventory, sessions, users, duration, freshness). It explicitly distinguishes itself from the sibling telemetry tools by naming the event, timeseries and session-facts alternatives, so an agent can route without opening any 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 gives an explicit entry-point instruction ('Start here') and an explicit exclusion ('call the event, timeseries or session-facts tool only for the question you need to answer' / 'do not fetch every page preemptively'). It also names a prerequisite guide tool for interpretation, leaving nothing to inference.

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