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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real context beyond them: in-flight runs keep their pinned versions, and the action creates a new Task version with activation. It does not clarify what happens to the superseded prior version, so it stops short of fully characterizing the destructive scope.

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?

Five short sentences, each carrying a distinct rule, with the core action front-loaded and the workflow guardrails after. No filler or restatement 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?

For a mutation tool with no output schema, the description covers the prerequisite (compile), the approval gate, the versioning effect on running executions, and the sensible next step. Nothing needed to invoke it correctly is missing, and annotations carry the safety profile.

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 100%, so the baseline is 3, but the description adds a non-obvious constraint on the plan parameter — it must come verbatim from compile and must never be hand-edited, with recompilation as the remedy. That is meaning beyond the schema's plain 'verbatim' note.

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 — freezing a reviewed plan as the Task's next version and activating it — which is unmistakably distinct from compile, run, or start siblings. An agent can tell exactly what state change this causes without opening the 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?

Explicit sequencing: freeze ONLY after the user has seen the proposal and approved, pass the exact plan object from workbench_tasks_compile, never hand-edit (recompile instead), and offer a first run afterward. It names the prerequisite (compile) and the gating condition (user approval) directly.

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