get_session_stats

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

With readOnlyHint already covering safety, the description adds real behavioral context: the savings counter is modeled (file bytes avoided minus bytes served; searches earn none) and the latency ring is volatile, cleared by a server restart. These are non-obvious traits an agent could not derive from the annotations or empty schema.

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 sentences, front-loaded with the return contract before the operational caveats, and every sentence carries information. The inline JSON-ish field list is slightly dense but is the most load-bearing part of the description.

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 correctly carries the return-value burden by naming both fields and explaining how total_tokens_saved is computed. Minor gaps remain (units/format for latency_per_tool, whether the counter is cumulative per session), but for a zero-parameter read tool this is nearly complete.

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 tool takes zero parameters, so the baseline is 4 and there is no schema surface for the description to elaborate on. The description's inline return-shape detail is useful but belongs to output rather than parameter semantics.

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 opens with a specific verb+resource ('Session self-monitor: returns...') and immediately enumerates the returned fields, so an agent knows exactly what comes back. It explicitly names the sibling it is not (analyze_perf), which removes ambiguity among a large set of stats tools.

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?

It routes windowed analysis to analyze_perf, giving a concrete condition for choosing the alternative. It also flags the tool's lightweight/in-memory nature, though it does not spell out an explicit 'when not to use' beyond the analyze_perf redirect.

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