List Sessions

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, freeing the description from safety disclaimers. The description adds valuable behavioral context by explaining WHY the default is summary ('to keep stdio transports bounded') and that detail='full' returns a 'bounded page of full metadata.' This reveals the tool's internal rate-limiting rationale, which is genuinely useful behavior not evident from annotations alone.

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, zero fluff. The first sentence states the core purpose, the second explains behavior, rationale, and points to the alternative. Every clause contributes to the user's decision-making: what, why, and when-not. The most important information is front-loaded immediately.

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 the tool has 5 parameters and no output schema, the description adequately covers the main usage decision (how to get full vs summary, and where to go for a single session). It could mention `outcome_filter` since that's a domain-specific filter, but the defaults and self-explanatory names reduce the ambiguity. The presence of annotations for read-only/idempotence fills the safety gap. Minor omissions prevent a 5, but the description is complete enough for an agent to use the tool correctly in most intended scenarios.

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 schema description coverage is 0%, so the description carries the burden of explaining parameters. It does explain the `detail` parameter's effect (summary vs full) and implies pagination via 'paginated,' which covers `limit` and `offset` conceptually. However, it leaves `outcome_filter` and `response_format` unexplained, and doesn't explicitly map the pagination wording to the parameter names. The description adds meaning for the most crucial parameters but still leaves the agent to infer the rest from names alone.

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 clear verb-resource-scope triplet: 'List durable sessions saved under the local data directory.' This precisely distinguishes it from siblings like session_metrics or session_read, and the contrast with session_read is explicitly stated. The purpose is immediately understandable and differentiates from other session_* 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?

The description explicitly routes the agent: 'use session_read for one full session or detail='full' for a bounded page of full metadata.' This names the alternative tool (session_read) and provides the selection condition, leaving no ambiguity about when to choose this tool versus the alternative.

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