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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly explains the main effect: the next call uses the rolled-back version's source. However, it does not mention reversibility, potential side effects (e.g., whether the rollback is permanent until changed again), permission requirements, or what happens if an invalid version is provided. It does indirectly mitigate version validation by pointing to host.tool_history, but lacks comprehensive behavioral detail.

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?

The description is two sentences with no filler. It front-loads the core action, explains the immediate consequence, and includes a practical reference to a sibling tool. Every sentence earns its place; there is no redundant information.

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 simple 3-parameter tool with no output schema, the description covers the essential action, the effect on subsequent calls, and points to where valid version numbers can be found. It does not mention return values or error conditions, but given the tool's simplicity and the explicit reference to host.tool_history for validation, it is sufficiently complete for an agent to invoke it correctly. A minor gap is the lack of clarification on whether the rollback affects all future calls until changed again, though this is implied.

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%, so all parameters have descriptions. The description adds some value by directing the agent to host.tool_history for valid version numbers, which provides context for the 'version' parameter. It does not add further semantics beyond the schema, such as naming conventions or error handling. Since the baseline for 100% coverage is 3, and only a minor extra is added, a 3 is appropriate.

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?

The description clearly states the action: 'Make an earlier published version of one of this tenant's tools current again.' It also specifies the direct consequence ('the next host.tool_call runs that version's source'), which distinguishes it from sibling tools like host.tool_publish (which creates new versions) and host.tool_history (which only lists versions). The verb-resource pair is unambiguous and well-differentiated.

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?

The description provides a clear usage hint by instructing the agent to 'See host.tool_history for the valid version numbers,' which sets a prerequisite. It implies the tool is used to revert to a prior version but does not explicitly state when not to use it or compare it to alternatives like host.tool_publish or host.tool_diff. The guidance is adequate but lacks explicit exclusions or a full decision tree.

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