start_session

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=false. The description adds real context beyond them: commands must be allow-listed, execution is asynchronous, and output is retrieved via read_session. It omits the important behaviors though — what happens when a command is rejected by the allow-list, whether the session persists, and that stop_session governs its lifecycle.

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?

A single compact sentence, front-loaded with the action and followed by the essential follow-up step. No filler, no repetition of the tool name.

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?

An output schema exists, so return values need not be explained. But for a destructive, non-idempotent launch tool with zero-described parameters, the definition leaves too much open: the confirm gate, allow-list failure behavior, and session cleanup are all unaddressed.

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 0% across three parameters, and the description adds no meaning for any of them. The 'confirm' boolean is especially consequential on a tool flagged destructive, and neither the schema nor the description explains when it must be set or what 'cwd' defaults to.

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 states a specific verb plus resource ('Start an allow-listed command') and adds the key execution mode ('in the background'), which implicitly separates it from the foreground run_command sibling. It doesn't name run_command explicitly, so the differentiation is inferred rather than stated.

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?

It gives a useful follow-up pointer ('read its output with read_session'), so the agent knows the next step in the workflow. However, it never says when to prefer this over run_command, nor when not to use it, leaving the choice between foreground and background execution to inference.

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