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

With annotations already declaring readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the safety profile is fully covered by structured data. The description adds a small slice of behavioral context by specifying that the tool reports both 'platform' and 'adapter' versions, implying a composite return value. However, it doesn't describe the output format or whether any network/session state is accessed. Per the calibration examples, this is 'adds some value but not rich behavioral context' — a 3. There is no contradiction with the annotations, so this scores normally.

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 a single, front-loaded sentence: 'Show the current MCP platform and adapter versions.' Every word carries weight, with zero redundancy or filler. It's appropriately sized for the tool's utterly minimal scope.

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 zero-parameter, read-only version tool with strong annotations, the description is essentially complete: it clearly states the operation and the full scope of what's versioned (MCP platform + adapter). The only gap is that presenting 'versions' usually implies returning data, and with no output schema available, a brief note about the return shape would have been nice. However, for the trivial complexity at hand, this is negligible, so a 4 is fair.

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?

The tool has zero parameters, so per the rubric, the baseline is 4 — there is nothing the description needs to add about parameter semantics. The schema coverage is trivially 100%, and the description correctly does not pad itself with irrelevant parameter documentation. The only reason it's not a 5 is that the description also doesn't add any meta-information (like configuration or versioning) that could meaningfully enrich the parameter topic, but that's a minor quibble.

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 uses a specific verb ('Show') and a clear resource ('current MCP platform and adapter versions'), making the tool's purpose immediately obvious. The description clearly separates it from obvious siblings like authenticate, connect, and report_bug. However, it stops short of a 5 because it doesn't differentiate itself from the potentially overlapping 'toolkit_info' sibling, and the rubric caps at 4 for 'clear but no sibling differentiation'.

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 no explicit guidance on when to use this tool versus alternatives, and no mention of exclusions or prerequisites. The usage context is implied by the tool name and purpose — an agent would reasonably infer that this is for a version check — which earns the 'implied usage' 3. No credit is lost for complexity here, but there's also no extra guidance credited beyond the implied.

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