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

Annotations declare destructiveHint=true, and the description goes well beyond that by scoping the damage: it is a versioned activation, and in-flight runs keep their pinned versions. It also surfaces a confirmation discipline ('echo what you're freezing in one line first') that the destructive annotation alone would not convey.

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?

Four sentences, each carrying a distinct obligation: what freeze does, how to pass the plan, when it is permitted, and what follows. The irreversible action and its precondition are front-loaded with zero filler.

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 essential agent concerns: the source of the plan argument, the confirmation gate, the effect on running work, and the natural next step. Nothing an agent needs in order to call it safely is missing.

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 real meaning for the plan/sentence pair: the plan must be the verbatim object a compile returned, and if the sentence changes the plan must be recompiled rather than edited. That is a coupling constraint the schema does not express. It says nothing extra about workspace or approvalId.

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 (freezes) plus the exact outcome: turns a reviewed plan into the Task's next version and activates it. It also distinguishes itself from workbench_tasks_compile by requiring output from that tool and by describing the activation step, which no sibling performs.

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 preconditions (only after the user has seen the proposal and said go), an explicit anti-pattern with the correct alternative (never hand-edit the plan; change the sentence and recompile), and a post-action recommendation (offer to start a first run). Nothing about when to reach for this tool is left to inference.

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