replay_stats

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

Annotations declare readOnlyHint=true, which the description aligns with by framing as analytics (read-only). The description adds context about the scope (all recorded sessions) and the breakdowns provided, which is useful. However, it doesn't disclose potential performance implications of scanning all sessions, pagination, or how the output is structured. With annotations covering safety, the description adds some value but could include more behavioral detail.

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 description is a single dense sentence listing the key metrics, followed by a short clause on filters. It is front-loaded with the core analytics content. It earns its length by covering multiple dimensions of the stats without fluff. Could be slightly more structured but is effective.

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?

ันGiven that the output schema is absent and the tool returns complex aggregated analytics, the description provides a good overview of what is returned (death-cause breakdown, tool mix, per-project rollups) which partially compensates. However, it does not explain how the results are presented, whether there are any limitations on data range, or how 'error rate' is calculated. For a cross-session aggregation tool, these details could be useful, but the description covers the essentials.

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%, with descriptions for both 'limit' (N most recent sessions) and 'project' (sessions whose project dir contains this). The description mentions 'Optional limit / project filter', which aligns with the schema. No additional semantics beyond schema, which is acceptable given full coverage.

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 clearly identifies the tool as providing cross-session analytics, enumerating specific metrics (tool calls, error rate, death-cause breakdown, tool mix, per-project rollups). It distinguishes from siblings like replay_sessions (listing sessions) and replay_insights (likely more focused analysis) by emphasizing aggregate stats across sessions. Could be more explicit about which sibling it differs from, but the purpose is clear and specific.

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?

The description implies usage for analytics on all recorded sessions, but does not explicitly state when to prefer this over replay_sessions, replay_insights, or replay_status. The optional limit and project filter are mentioned, giving some context on scoping, but no explicit when-not or alternative selection guidance.

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