Start a Claude Code session

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and idempotentHint=false, so the safety profile is covered. The description adds real context beyond that: the session runs in the background on the user's Mac and Claude Code sees only the supplied text, which is a critical behavioral constraint about context isolation. It does not mention that repeated calls create independent sessions or how results are retrieved, which keeps it from a 5.

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 short sentences, front-loaded with the action, then the critical writing constraint, then the continuation path. Every sentence carries distinct, actionable information with no repetition of the name or schema.

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, yet the description never says what comes back — notably the session identifier needed to call send_message, read_messages, or end_session later. The 'wait_seconds' parameter hints that an answer may arrive inline, but the return contract is left implicit, which is a meaningful gap for a tool that creates a persistent resource.

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 the baseline is 3; the description earns an extra point by reinforcing the semantics of 'message' with the non-obvious constraint that Claude Code sees only this text, which tells the agent the brief must be self-contained. It adds nothing about 'wait_seconds' or 'workspace' beyond the schema, but those are already well documented.

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 ('Start a new background Claude Code conversation on the user's Mac') plus the immediate follow-on action ('send it the first message'). It also differentiates itself from the sibling send_message by framing that tool as the continuation path, so an agent can distinguish start vs. continue without reading schemas.

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?

Gives clear usage context and names the alternative for the follow-up case ('Continue it later with send_message'), which routes the agent correctly between the two session tools. It stops short of stating when not to start a session (e.g., when one already exists, pointing at list_sessions), so it is clear but not fully exclusive.

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