List LLM sessions for a specific agent to view grouped conversation turns, with cursor-based pagination. Use get_llm_session for detailed metrics.
List LLM sessions (grouped conversation turns) for one agent (required).
Cursor-paginated; page_size is capped at 100. Use get_llm_session for a session's aggregate cost/tokens/turns plus the full per-turn list.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | ||
| cursor | No | ||
| agent_id | Yes | ||
| sort_dir | No | ||
| page_size | No |
Changes observed during successful MCP inspections.
v0.2.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and it delivers the key behavioral fact for a read-only list tool: results are cursor-paginated and page_size is capped at 100, a constraint the schema alone doesn't express. It omits auth/permission requirements and return shape, keeping it out of 5 territory.
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 short sentences, front-loaded with the core purpose and scope. The pagination/cap detail and the sibling routing both earn their place with no filler.
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 list tool with no output schema and no annotations, the agent still lacks the shape of a returned session and the accepted sort/cursor semantics. Pagination and sibling routing are covered, but the return contract and remaining parameter semantics leave real gaps.
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?
Schema description coverage is 0% across 5 params, so the description must compensate. It does cover the required agent_id and the page_size cap (useful beyond the schema's default of 25), but sort, sort_dir, and cursor are left entirely unexplained, including no indication of valid sort fields or direction values.
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?
States a specific verb and resource (list LLM sessions) and even defines the resource ('grouped conversation turns') and its scope ('for one agent (required)'). This clearly separates it from get_llm_session, which is named in the same description.
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?
Names the alternative get_llm_session and the condition that selects it (aggregate cost/tokens/turns plus per-turn list), so the agent knows which tool to pick. It doesn't state an explicit when-not-to-use forward (e.g., bulk export or cross-agent queries), so it falls just short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.