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

The description adds value beyond the annotations: it clarifies that the tool is non-destructive (readOnlyHint=true) but also explains the output is a 'labeled strategy card' that helps shift perspective. It doesn't contradict annotations. It adds contextual detail (random selection, card format) but doesn't delve into specifics like whether the card has title, description, or instructions—though with no output schema, that gap is acceptable. Without annotations, it would still be decent, but with annotations covering read-only, the description earns a 4 for adding behavioral context.

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 relatively concise, but it repeats the purpose multiple times: 'stuck in a single way of thinking, facing opposition, or need to see the problem from a completely different angle' and later 'change your perspective, reverse assumptions, adopt alternative viewpoints' are redundant. Some trimming would improve, but it's still front-loaded with the core action (random Reframe strategy) and essential guidance. It's not wasteful enough to drop below 4.

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 tool with no output schema, the description covers what an agent needs: when to call it and what to expect (a labeled strategy card). It doesn't specify the exact structure of the card, but that's a minor gap. It lacks explicit exclusions (when not to use), but the purpose is narrow, so completeness is high. The mention of the card's purpose adds context, so a 4 is warranted.

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?

With zero parameters and 100% schema coverage (which is trivial for empty properties), the description doesn't need to explain parameters. The baseline for zero params is 4, and the description instead focuses on usage context, which is appropriate. It adds no parameter-specific info because there are none, but that's fine.

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 it returns a random Reframe strategy, with a specific purpose (breaking mental ruts) and explicitly mentions usage scenarios (stuck, opposition, different angle). It also differentiates itself from siblings by naming the specific category (Reframe), though it doesn't explicitly compare to siblings, the category name is distinctive enough.

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?

Provides explicit 'when to use' conditions: 'when stuck in a single way of thinking, facing opposition, or need to see the problem from a completely different angle' and 'Best for breaking out of mental ruts.' It also lists example use cases: 'change your perspective, reverse assumptions, adopt alternative viewpoints.' This is clear guidance for an agent, though it doesn't mention when NOT to use it, but given the narrow purpose, it's sufficient.

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