Initialize Claude Project History Session

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

Annotations declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint. Description adds behavioral context: it is the only proactive call, returns specific context fields, and includes a hint. No contradiction.

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?

Well-structured with bold call-to-action, explanation, then args list. Slightly verbose but each sentence adds value. Could be trimmed slightly but overall efficient.

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?

Describes return type (SessionContext with fields) and depth behavior. Lacks error handling or invalid workflow_id scenarios, but given the tool's simplicity and no output schema, it is largely 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?

Description elaborates on each parameter beyond schema: workflow_id source (CLAUDE.md), cwd purpose (current working directory), depth levels with token estimates and content breakdown. Adds significant value.

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 it should be called first at the start of every session and explains it returns orientation context (active tasks, open blockers, decisions). It distinguishes itself from siblings by noting it is the only proactive tool and lists tools not to call afterward.

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?

Clear when to use (first thing in session) and what not to use afterward (workflow_summary, task_list, decision_list). Provides depth parameter guidance and advises pulling individual records on demand.

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