session_start

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

With no annotations, the description carries the burden of disclosing side effects. It explains that python3/node get a stateful REPL with persistence, other languages get a workspace, and a session_id is returned. It does not cover lifecycle aspects like whether sessions need to be explicitly stopped, but it is transparent about the core behavior without contradicting any annotations.

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 sentences long, front-loaded with the primary purpose 'Start a persistent session,' and every clause adds value—explaining language-specific behavior and the return value. There is no redundancy or unnecessary detail.

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 tool with one optional parameter and no output schema, the description adequately covers purpose, language-specific behavior, and return value. It does not mention session_id usage in subsequent calls or error handling, but the sibling tool names (session_run, session_stop) imply the workflow, making it reasonably complete without over-explaining.

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?

The schema has only one optional parameter 'language' with 0% coverage and no enums, so the description compensates by explaining the semantic difference: python3/node yield a stateful REPL, while other languages yield a persistent workspace. This adds meaningful meaning beyond the raw schema, though it does not enumerate all possible language values.

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 'Start a persistent session' with a specific verb and resource. It further distinguishes behavior for python3/node versus other languages, making it distinct from sibling tools like execute_code that likely run one-off code. The return value (session_id) is also specified, adding to clarity.

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 provides clear context: use this to start a persistent session where variables/imports persist or a workspace directory is created. However, it does not explicitly mention when not to use it or name alternatives like execute_code for one-off execution, so it stops short of full 'when/when-not' guidance.

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