session_start

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

With no annotations, the description carries the full disclosure burden. It explains persistence semantics, language-specific behavior (stateful REPL vs workspace directory), and the returned session_id. It does not mention session lifecycle management (e.g., needing session_stop), but the core behavior is transparent.

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 sentences, front-loaded with the main action, then conditional details. No filler; every clause adds value. The structure is efficient and easy to parse.

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 tool is simple (one optional parameter, known return value), and the description covers starting behavior, language effects, and the return value. It gives an agent sufficient information to invoke the tool correctly without consulting siblings. The output schema is noted but not necessary.

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 0%, but the description fully compensates by explaining how the 'language' parameter affects behavior: python3/node get a stateful REPL with persisting variables/imports, while other languages get a persistent workspace. This is far more informative than a typical schema description.

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?

Description opens with a specific verb+resource ('Start a persistent session'), clearly distinguishing this from sibling session tools (session_stop, session_list) and code execution tools (execute_code). It further clarifies language-specific behavior, leaving no ambiguity about the tool's function.

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 implies when to use this tool: when a persistent session or stateful REPL is needed across execute_code calls. It does not explicitly name alternatives or exclusions, but the context is clear that this is the entry point for persistent sessions, especially for python3/node.

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