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

Annotations only declare it is not read-only, not destructive, and not open-world. The description goes well beyond that: lifecycle ('Sessions unused for 30 days, or the least recently used past 500, are forgotten; their folders stay') and path-resolution semantics ('Relative file paths and commands without cwd use that workspace; ~ still means home'). These are exactly the behavioral details an agent cannot infer from the 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?

Front-loaded with the action and its product, then moves through retention, path semantics, and scope in tight sentences with no filler. Dense but every clause carries information; slightly long, though nothing is redundant.

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 creation tool with no output schema and only four parameters, the description covers the essential unknowns: what is created, the retention rule, path resolution, and what the session does not control. The remaining gap is the meaning/format of name and workspaceRoot, which neither schema nor description fully addresses.

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 50%: deviceId and workSessionId are self-documented, while name and workspaceRoot are not. The description adds real meaning for workspaceRoot by explaining relative-path and cwd resolution, plus the role of the returned workSessionId. However, it never explains name or workspaceRoot's own format, so it does not fully compensate for the coverage gap.

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?

States a specific verb and resource ('Create a separate work session ... and a unique workspace folder') and immediately scopes it to 'this AI conversation', which distinguishes it from get_work_session and list_work_sessions. An agent can tell what it produces and why without opening a schema.

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?

Gives explicit operational guidance: 'Keep the returned workSessionId and pass it on every subsequent call, including process output and undo.' It also clarifies what this session does and does not govern ('separates activity and process control, not access to shared absolute paths or the physical browser'). It stops short of naming sibling alternatives explicitly, but the when-to-use condition is unambiguous.

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