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

The annotations only declare readOnlyHint=true. The description adds substantial behavioral context: flow entries are classified once and cached in Redis, a cold session costs one report load while warm sessions cost nothing, and the dataset rebuilds automatically on a change heartbeat. This far exceeds the annotation baseline and helps the agent reason about performance and statefulness.

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?

Three dense sentences, each serving a distinct purpose: definition/mechanics, performance profile, and invocation sequence with siblings. No fluff. The only slight blemish is the unexplained jargon 'build basis-t', which may confuse an agent, but overall the structure is tight and front-loaded.

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 there is no output schema, the description properly explains the returned sessionkey's role and the full session lifecycle: open, pass to evaluator tools, and automatic rebuild on heartbeat. It also covers cost and sibling comparisons, making the tool complete for an agent to invoke correctly.

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 input schema is an empty object with zero parameters, so there is nothing for the description to clarify about parameters. Per the rubric, a zero-parameter tool earns a baseline of 4, and the description correctly focuses on output behavior (the sessionkey) instead.

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 begins with a specific verb-resource pair ('Open a report session') and immediately expands on what that means (classify flow entries once, cache, fast path for interactive report screens). It also names the sibling tools it is not (evaluate_report_session, evaluate_report_batch, evaluate_report), making differentiation unambiguous.

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?

Usage guidance is explicit: 'Call this first, then pass the sessionkey to evaluate_report_session (one view) or evaluate_report_batch (many at once); for a single one-off report without a session use evaluate_report.' This tells the agent exactly when to use this tool vs. its alternatives, with no inference required.

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