session_start

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It thoroughly explains side effects: existing tmux sessions are returned as-is, fresh sessions are minted a UUID, claude_session_id triggers resume, default permission mode is bypassPermissions for unattended runs, worktree creates an isolated git worktree, and launch options are stored and reused. This is excellent transparency about behavior and defaults.

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?

The description is well-structured with a front-loaded purpose and bullet-pointed details. It avoids fluff, and each bullet adds distinct value. However, it is somewhat longer than necessary, and some details (like effort values) could be implied from schema defaults, though schema has no descriptions. Still, it earns a solid 4 for organization and efficiency.

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 complexity (11 parameters, no annotations, no output schema), the description covers many important behavioral aspects: session behavior, UUID minting, resume, permission mode, worktree, and launch option reuse. It does not explicitly describe return values or error conditions, and it omits explanations for several parameters. However, the coverage is substantial and would likely enable an agent to use the tool correctly in most cases.

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%, so the description must compensate. It adds meaningful semantics for several parameters: permission_mode with enumerated values and default, worktree with path pattern, effort values, claude_session_id resume behavior, and allowed_tools as a restriction. However, it leaves 5 of 11 parameters unexplained (model, add_dir, working_dir, disallowed_tools, append_system_prompt), some of which are not self-evident. It covers the key parameters but the gaps prevent a higher score.

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 explicitly states 'Pre-create a Claude Code session' with a clear verb and resource, and immediately distinguishes from the sibling tool session_send ('creates one on demand'). This goes beyond a simple definition by explaining the specific use case of fixing launch options up front.

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 directly addresses when to use this tool: 'Usually unnecessary' for most cases, but 'useful to fix launch options up front.' It explicitly names session_send as the alternative that creates sessions on demand. This provides clear usage guidance and a when-not-to-use caveat.

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