session_stats

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds the behavioral trait of returning aggregate numbers rather than per-session rows, which is useful, but does not disclose return structure or additional constraints.

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?

Tight, structured description with a clear READ label, purpose statement, comparison to sibling, and parameter documentation. Every sentence earns its place with no redundant text.

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?

For a simple read-only stats tool with one optional parameter and strong annotations, the description conveys purpose, scope, and parameter semantics. The absence of a return schema is mitigated by listing the key stats returned (concurrency, busiest pools).

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 parameter 'target' is fully explained: it is a Horizon target from config.yaml, and omitting it uses the default. This adds meaning beyond the schema's simple type and default, making the parameter's purpose clear.

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 provides session statistics with specific breakdowns (concurrency by state/protocol, current concurrent, busiest pools) and explicitly distinguishes it from session_list as the aggregate reporting counterpart.

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 explicitly frames usage: 'The reporting counterpart to session_list — aggregate numbers, not per-session rows.' This tells the agent when to use session_stats instead of session_list, giving a direct alternative.

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