Predict MITRE Transitions

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

Beyond the read-only/idempotent annotations, the description explains how each row is generated: attack_flow rows come from analyst-authored DAGs, mitre_canonical is inferred from tactic rank, and blended has both. It also discloses the limitation that ~24% of real transitions are inexpressible by the canonical basis, which is valuable 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?

Every sentence adds distinct information: purpose, evidence-basis semantics, preference recommendation, and direction intent. The structure is front-loaded with the core prediction behavior followed by necessary nuance, with no wasted words.

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 the rich parameter schema, enums, output schema, and annotations, the description is sufficiently complete. It covers what the tool returns, how the data is derived, how to pick basis and direction, and a key limitation. Nothing necessary for successful invocation is missing.

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 input schema already documents all four parameters, so the baseline is 3. The description adds operational meaning for basis (attack_flow vs mitre_canonical vs blended) and direction (forward vs reverse) beyond the schema descriptions. It does not add much for top_n or technique_id, but the schema covers those sufficiently.

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 opening sentence names the specific action (predict), resource (MITRE ATT&CK techniques), and conditionality (follow/precede a given technique) with probabilities and examples. This clearly distinguishes the tool from sibling functions focused on coverage, technique details, or raw attack flows.

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 explicit usage direction: prefer attack_flow evidence, use forward to anticipate the next step, and reverse to infer what came before. It also explains which basis to prefer and why, giving an agent actionable selection criteria.

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