pi_start_session

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

Annotations only indicate this is not read-only, not open-world, and not destructive. The description adds meaningful behavioral detail beyond that: sessions create an output namespace under specific directories, persist across restarts, and make the latest session current. This helps the agent understand side effects and lifecycle 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?

Two compact sentences deliver the core action, the namespace structure, and the persistence/current-session behavior with no filler. The essential purpose is front-loaded, and every clause adds value.

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?

For a simple create operation with two optional, fully documented parameters and no output schema, the description covers the main facts an agent needs: what is created, where it lives, and its persistence/current-session effect. It lacks only an explicit pointer to sibling tools for session switching, which is a minor gap.

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%, and the schema already explains both 'name' and 'target_dir' clearly, including the target_dir working-files behavior. The description adds no new parameter-level meaning, so the baseline score of 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 opens with a specific verb and resource: 'Create a new processing session.' It adds concrete detail about what a session is (an output namespace under work/, previews/, checkpoints/) and notes persistence and current-session semantics, which clearly distinguishes it from sibling tools like pi_list_sessions, pi_use_session, and pi_end_session.

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 useful context about sessions persisting and the latest being current, but it never says when to create a new session versus using or ending an existing one. Sibling tools like pi_use_session and pi_end_session exist, yet no alternative or exclusion is mentioned, leaving the agent to infer the appropriate workflow.

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