replay_insights

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

With no annotations provided, the description must fully disclose behavioral traits. It only lists output fields but fails to mention whether the operation is read-only, if it has side effects, required permissions, error behavior for invalid session IDs, or performance implications. The description does not compensate for the missing annotation burden.

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 sentence listing multiple metrics, which is moderately concise but not optimally structured. It front-loads the key concept ('per-session insight metrics') but the list of metrics becomes dense. Adding bullet points or a clear delimiter would improve readability. The sentence is not overly long but could be more efficient.

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?

There is no output schema, so the description must cover return values. It lists several metrics but lacks details on data types, units (e.g., duration in seconds?), formatting, and edge cases (e.g., what happens if session_id is invalid or the session hasn't ended). It also doesn't explain how 'most-used tools' is represented. This incompleteness may lead to incorrect expectations.

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% (the single parameter session_id has a description stating default behavior). The tool description adds context about the returned metrics but does not enhance understanding of the parameter beyond what the schema already provides. 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 returns 'per-session insight metrics' and lists specific metrics like duration, tool-call count, error count/rate, and files touched. It uses a specific verb (retrieves) and resource (session insights), making the purpose clear. However, it does not explicitly differentiate from sibling tools like replay_stats or replay_sessions, leaving some ambiguity.

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 when to use (to get detailed session metrics) but provides no guidance on when not to use, alternatives, or prerequisites. For example, it doesn't contrast with replay_stats (aggregate) or replay_sessions (list sessions). This lack of usage context forces the agent to infer appropriateness.

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