start_session

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

With no annotations, the description must carry the full behavioral disclosure burden. It tells the agent that the tool starts or resumes session tracking and should be called automatically, but it does not explain what happens when a session is already active, whether callings is idempotent or destructive, or what state changes occur. Some of this is implied by force_new in the schema, but the description itself leaves the side effects underspecified.

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 four short, purposeful sentences with no filler. It front-loads the purpose, then gives usage triggers, a required follow-up action, and an exclusion. The emphasis on 'AUTOMATICALLY' and 'Do NOT' improves scannability without bloating the text.

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 is largely complete for invocation: it states purpose, provides examples and exclusions, names the next tool to call, and all parameters are covered by the schema. It falls short only on explaining the precise 'resume' semantics and side effects on the active session, which would matter when deciding between start_session and related tools like get_active_session or end_session.

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 every parameter is already documented in the schema. The description only adds 'current project,' which maps to workspace_path, but it does not enrich goal, title, or force_new beyond what the schema already states. Baseline 3 is appropriate.

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 a specific action—'Start or resume Session Memory tracking'—scoped to 'the current project,' and the schema confirms workspace_path as the project identifier. This distinguishes it from siblings like end_session, get_active_session, and get_context by naming the session lifecycle action it performs.

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 gives explicit when-to-use guidance: 'Call this AUTOMATICALLY at the beginning of meaningful project work' with concrete examples, and an explicit when-not: 'Do NOT start sessions for trivial questions.' It also instructs the agent to follow with get_context. It does not name alternative sibling tools for checking or ending sessions, such as get_active_session or end_session, so it stops short of full alternative routing.

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