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

Annotations already declare non-readOnly, non-idempotent, non-destructive, closed-world; the description adds genuinely new behavior: a name mismatch opens nothing (fail-closed safety), the call is metered as one project read when startup is included, and startup is the only thing that costs extra. It doesn't cover session lifetime, expiry, or what happens when a session is already open for the device.

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 when-to-use condition, then the safety precondition, then the return payload and the optional startup bundling, then the discovery caveat. Dense with little filler, though a few clauses duplicate what the schema already states about expectDeviceName and metering.

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?

With five parameters (two required, one nested object) and no output schema, the description does the needed work: it names the returned fields, explains the optional nested startup object's payoff, and discloses the metered cost. Session lifecycle and error behavior beyond the name mismatch are the remaining gaps.

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 every parameter is documented in-schema, so the baseline is 3. The prose largely restates schema content (expectDeviceName mismatch, startup's policy/Git/task payload) with only a modest addition — that startup is optional and that the workspace lookup should be skipped when the ID is known.

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 ('opening a session') and scopes it to the explicitly selected device/workspace, making it clearly distinct from execution_session_close and from command execution tools. It also tells the agent what the call can bundle (session envelope plus optional startup context), so the tool's identity is unambiguous.

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 conditional guidance on the main decision points: include startup when you want policy/Git/task continuation in this same call, and 'Discover workspace IDs first only when unknown,' which saves an unnecessary lookup. It stops short of stating the dependency relationship with siblings (e.g. that command_run requires an open session) or when NOT to open one.

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