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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavioral caveats: only tracked sessions are counted, other_version_runs_excluded quantifies runs under a different version, and comparison is null for range=all. It does not mention auth or rate limits, but for a read-only reporting call those gaps are minor.

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 sentence is front-loaded, and the long metric enumeration is dense but each item is informative for an agent that cannot see an output schema. There is minor redundancy (the comparison-window point is stated twice, once in prose and once in the schema) and the single-paragraph form makes the metric list hard to scan.

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, this description carries the full burden of explaining the return payload, and it does so thoroughly — window metrics, comparison window, lifetime totals, outcomes, per-node reach/continue/response/loss rates, per-port branch splits, and the versions list. Combined with the tracking-only caveat, an agent has enough to interpret the result 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 description coverage is 100%, so the schema already explains id, range, channel and version, including the 7d/30d/90d/all enum and the comparison-null note. The description adds only modest value beyond that — chiefly that the response's 'versions' list is how an agent discovers valid version numbers not covered by an enum — so the baseline of 3 is appropriate.

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 opens with a specific verb and resource ('Get flow analytics') and immediately scopes it to 'the builder's Analytics panel for one flow', then enumerates the exact metrics returned. This distinguishes it clearly from siblings that deal with raw flow data (list_flow_sessions, list_flow_events, get_flow_definition) without the agent needing to open 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 useful scoping context — analytics are per published version, version defaults to the current one, and 'versions lists the others' — which tells the agent how to get meaningful results. However, it never names an alternative tool or states when to prefer raw session/event listings over aggregate analytics, so the when-to-use-with-what guidance is implied rather than explicit.

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