Predict Attack Path

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the agent knows it's a safe read operation. The description adds the crucial constraint that it requires Purple tier ($11.99/mo), which is beyond what annotations provide. No contradictions.

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?

Two sentences, first describes core functionality and output, second adds context and tier requirement. No wasted words, front-loaded with key 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?

Given no output schema, the description explains what is returned (top-N transitions with probability, transition_count, example threats). It covers the essential behavior for a prediction tool. Could mention error handling or data freshness, but overall adequate.

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 baseline is 3. The description adds meaning by specifying the output format (probability, transition_count, example threats) which is not in the schema, and implies the role of top_n and direction ('forward/reverse') though not explicitly mapped. This adds value beyond schema definitions.

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 specific verbs ('predict', 'returns') and identifies the resource (MITRE technique, observed chains) and output (top-N transitions with probability, transition_count, example threats). It clearly distinguishes from siblings which are mostly get_* or search tools, none of which perform attack path prediction.

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 states it powers attack-chain reasoning and requires Purple tier, giving context on when it's appropriate. It doesn't explicitly exclude cases or name alternatives, but among siblings there's no similar tool, so usage is well implied.

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