eval_replay_reading_sessions

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

With no annotations, the description adds context: the constraint about query text and root default. But it doesn't mention side effects, idempotency, or performance implications for a replay operation.

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?

Two sentences, each earning its place: first gives purpose and root behavior, second adds a key constraint. No redundancy or fluff.

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?

Given an output schema (so return values need no explanation) and only two parameters, the description covers the tool's core functionality well, though 'limit' remains unexplained, leaving a minor gap.

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?

The description explains the 'root' parameter's default behavior ('If root is omitted, the MCP process project root is used'), but does not address the 'limit' parameter which remains undocumented, leaving a gap despite low schema coverage (0%).

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 specifies the tool's action ('Replay captured search reading-session events') and its purpose ('to detect retrieval drift'), clearly distinguishing it from sibling tools like eval_export_reading_sessions.

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?

Provides usage context: omitted root defaults to project root, and a constraint on replayability (only events with query text enabled). However, no explicit guidance on when to use this tool over alternatives like eval_export_reading_sessions.

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