replay_stats

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

No annotations exist, so the description must carry the full burden of behavioral disclosure. The description implies a read-only operation by listing computed statistics, but it does not explicitly state that no data is modified, nor does it mention authorization, rate limits, or behavior with empty data. The lack of explicit safety guarantees is a gap, but the nature of the tool (analytics) provides reasonable inference.

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 extremely concise—two sentences, 25 words—with no wasted words. It front-loads the core purpose ('Cross-session analytics') and immediately lists the specific metrics. Every sentence earns its place, and the structure is clear and scannable.

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?

The tool has no output schema, so the description must adequately convey the return value. It lists the key metrics (total tool calls, error rate, death-cause breakdown, tool mix, per-project rollups), giving a solid picture of the output. However, it does not describe the format (e.g., JSON object, array, aggregation method) or edge cases (e.g., empty sessions). For a simple analytics tool with only two optional params, this is largely sufficient but not exhaustive.

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 both parameters already having clear descriptions ('Only the N most recent sessions' and 'Only sessions whose project dir contains this'). The description adds a brief mention of 'Optional limit / project filter' but does not add new meaning beyond restating what the schema already conveys. Without additional semantic depth, the baseline score 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 clearly states the tool's purpose: 'Cross-session analytics across all recorded sessions.' It then lists specific metrics (total tool calls, error rate, death-cause breakdown, tool mix, per-project rollups), which leaves no ambiguity about what the tool does. This distinguishes it from siblings like replay_sessions (list sessions) or replay_insights (likely deeper analysis) by emphasizing aggregate statistics.

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 implicitly conveys usage for obtaining aggregate session statistics, but it does not explicitly state when to use this tool versus alternatives (e.g., replay_sessions for raw session data, replay_insights for deeper patterns). No when-not guidance or alternative tool names are mentioned, which is a gap given nine sibling tools.

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