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

Annotations already establish readOnly/idempotent/non-destructive, so the description rightly spends its words elsewhere: it discloses content boundaries ("Never who the visitor was or what they typed") and the derived-signal types (rage clicks, stuck). It omits operational traits an agent would want — behavior when a session id is unknown, or whether large sessions are truncated.

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?

Roughly three sentences, front-loaded with the outcome, then the contents, then the privacy boundary and the input source. No restatement of the name or title, and every clause carries new information.

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 steps in and characterizes the return shape as an ordered step list with errors and signals, which is exactly what an agent needs to plan a follow-up. Minor gaps remain: no mention of empty/unknown-session behavior or result-size limits.

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 50%: project is documented inline, session_id is not. The description clarifies session_id by pointing to where it comes from (an incident's evidence), but says nothing about project, the more ambiguous parameter in a multi-project token context. Baseline 3 fits given partial 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?

"What happened in one visit, step by step" names a specific verb (replay a visit) and resource (a single session's step sequence), then enumerates the payload: pages, clicks, failed requests, errors, and Relia-detected patterns. That scope distinguishes it from siblings like relia_trace (distributed tracing) and relia_logs (log search) without needing their schemas.

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?

"Takes a session id as found in an incident's evidence" gives a concrete entry point and implies this follows an incident investigation, which is useful. But it never states when NOT to use it or names an alternative (e.g., relia_trace for cross-session or latency questions), so the routing decision is left to inference.

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