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

Annotations only declare the mutation/safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false). The description goes well beyond them: it discloses prerequisites, optimistic-concurrency behavior via expectedRevision ("Checks the original world version so concurrent editor changes are preserved"), explicit conflict handling with a "never force overwrite" rule, and the non-publishing guarantee. That is exactly the behavioral context structured fields cannot carry.

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 purpose, then proceeds through prerequisites, concurrency, conflict handling, and the publishing caveat in tight declarative sentences. Slightly long, but essentially every sentence adds a distinct operational fact and none 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 mutation tool with no output schema and fully undescribed parameters, the description covers prerequisites, concurrency, conflict resolution, and publish semantics, which is most of what an agent needs. The gap is parameter-level meaning (three required, undocumented params), which is the one area left thin.

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 0% and none of the three required parameters carries a description, so the description must compensate. It only obliquely explains expectedRevision ("checks the original world version") and never clarifies workspaceId versus the referenced codeWorkspaceId or their relationship, leaving two of three parameters unexplained.

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?

Names a specific verb and resource ("Save the current staged package as one verified Worldstream draft") and adds the key distinguishing constraint "Saving never publishes," separating it from publish/save_* siblings. It stops short of naming the validate_world_code_workspace or inspect_world_code_workspace siblings it depends on, so an agent must infer the distinction rather than being routed explicitly.

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?

States clear preconditions for use ("Requires current validation, passing desktop/mobile inspections and at least one exercised custom control") and prescribes the conflict path ("open the latest world and reapply only requested changes"). It gives strong when-to-use context but never names the prerequisite tool (validate_world_code_workspace) or any alternative, leaving the workflow routing to inference.

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