session_init

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

No annotations are provided, so the description carries the behavioral burden. It discloses a new session is created, that it supports tree structure via parent_session_id, and that it is intended as the start of a session. However, it does not reveal the return value (likely a session ID), whether it persists state, or what happens if a session already exists.

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, with the core action and timing front-loaded. Every sentence adds useful context and there is no redundancy or 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?

The description adequately covers why, when, and with what parameters to call the tool. But with no output schema and no annotations, it should also tell the agent what the tool returns (e.g. a session ID to use with sibling tools) — that is missing, leaving the definition short of complete.

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 even without extra parameter detail. The description adds only light rephrasing — 'current project' for project_root and 'continue from a previous session (tree structure)' for parent_session_id — without adding new constraints or formats.

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 (Initialize), resource (CogSession), and scope (current project). The word 'new' and phrase 't the START' clearly separate this from siblings like sesssion_load, sesssion_update, and sesssion_checkpoint.

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 says to call this at the START of a Claude Code session, which gives a clear invocation context. It also explains when to provide parent_session_id (continue from previous session) and focus (session topic), though it does not name alternative tools for non-start cases.

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