session_start

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

No annotations are provided, so the description must disclose behavioral traits. It mentions what it returns (recent context, summary, metrics, memory) and the conditional nature of global memory. However, it does not clarify whether opening a session has side effects (e.g., creating a server-side resource, mutating state) or if it is a read-only operation. This leaves some ambiguity about safety and repeatability, though nothing contradicts known behavior.

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 two concise sentences that are front-loaded with the primary purpose and usage context. Every sentence contributes: the first states the action and result, the second provides usage guidance and return specifics. No filler or redundant information, making it highly scannable.

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 simplicity (2 optional params, no output schema, no annotations), the description covers the essential aspects: what it does, when to use it, and what it returns. It notes the conditional global memory. It does not detail error scenarios or side effects, but for a session start tool, this level of detail is largely adequate. A more explicit note on whether it is safe to call multiple times would push it to 5.

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 both session_key and context_query well-described in the schema. The tool description adds no additional semantic detail about these parameters, but the baseline for high schema coverage is 3. The description's mention of 'recent context' and 'summary' indirectly relates to context_query but does not elaborate on its usage beyond the schema.

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's function: 'Open a session and return recent context.' It specifies the verb 'open' and the resource 'session', and further details the return value ('summary of recent captures and correction alignment metrics'). This distinguishes it from sibling tools like session_checkpoint and session_end, which likely serve different phases of a conversation.

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 explicitly says 'Call this at the start of a multi-turn conversation', providing clear context for when to use it. It also mentions the return of project-specific and global memory 'when configured', which hints at conditional behavior. However, it does not explicitly contrast with alternatives (e.g., session_checkpoint) or state when not to use it, but the 'start' directive is sufficient for most scenarios.

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