memo_start_session

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

Annotations show readOnlyHint=false, confirming it's a write operation. The description adds that it creates or refreshes a tracked session checkpoint. It does not elaborate on side effects like whether calling it multiple times is safe or has cumulative effects, but it provides sufficient context given the annotations are minimal.

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 concise at 4 sentences, well-structured with clear intent, usage, parameter guidance, and a caution against misuse. Every sentence adds value, and the structure is front-loaded with the core purpose.

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 output schema exists (context indicates 'Has output schema: true'), the description does not need to explain return values. It covers purpose, usage, parameter semantics, and differentiation from sibling tools. For a session start tool, this is comprehensive.

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 coverage is 100% with descriptions. The description adds behavioral context beyond the schema: 'Pass session_id to continue a known session; omit it to create one. Pass cwd to bind the session to a project directory; omit it to use the current process directory.' This provides practical guidance not captured in the schema alone.

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 starts a new session for the client. It specifies it's a write tool that creates or refreshes a session checkpoint used by capture, grounding, and transcript lookup. It distinguishes itself from memo_save and memo_save_text by clarifying it is not for saving memories.

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?

Explicit usage guidance is provided: 'Call once at the beginning of a task or conversation.' It explains when to pass session_id (to continue a known session) vs omit (to create a new one), and when to pass cwd (to bind to a project). It also explicitly states when not to use the tool and directs to alternatives (memo_save/memo_save_text for durable content).

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