Claude Sessions

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

Discloses a key behavioral trait: the ledger is in-memory and resets on server restart, which is critical for understanding session persistence. With no annotations provided, the description carries the full burden and delivers clear, honest behavior beyond the basic listing function.

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 concise sentences: first explains output and ordering, second provides usage guidance and a behavioral note. No wasted words, front-loaded with core functionality.

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's simplicity (2 optional params, no output schema, no annotations), the description covers purpose, output fields, usage context with sibling tools, and the transient in-memory nature. Complete for effective agent invocation.

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 100%, so baseline is 3. The description adds no new meaning to the parameters beyond what the schema already provides (e.g., limit defaults to 10, workspace_dir is an optional filter). No extra context on parameter usage or constraints.

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 lists recent Claude conversations with specific fields (session_id, originating tool, workspace_dir, topic excerpt) and orders them newest first. It distinguishes itself from sibling tools like claude_continue and ask_claude by focusing on listing existing sessions.

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?

Explicitly tells when to use: when you lost a session_id or want to continue earlier work. Also provides guidance on next steps: pick the session and resume with claude_continue using the same workspace_dir. This contrasts with starting new sessions via ask_claude.

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