servicenow-mcp

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

No annotations are provided, so the description carries the full burden. It mentions 'Predictive Intelligence' and 'LightGBM algorithm', which gives some context about the underlying technology, but doesn't disclose key behavioral traits: whether this is a read-only prediction (likely, but not stated), accuracy expectations, rate limits, authentication needs, or what happens on failure. For an ML tool with zero annotation coverage, this is inadequate.

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, efficient sentence that states the core purpose and includes the algorithm detail. It's front-loaded with the main action. The algorithm mention adds value without being verbose. It could be slightly improved by structuring usage hints, but it's appropriately concise.

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 complexity of an ML prediction tool with no annotations and no output schema, the description is incomplete. It doesn't explain the output format (what the predictions look like), error handling, or integration context. The agent would lack crucial information to use this tool effectively, especially compared to sibling ML tools.

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%, with both parameters ('short_description' and 'description') well-documented in the schema. The description doesn't add any parameter-specific details beyond what the schema provides (e.g., it doesn't explain how the inputs affect prediction accuracy or format requirements). Baseline 3 is appropriate when the schema does the heavy lifting.

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 tool's purpose: 'Use Predictive Intelligence to predict category, assignment group, and priority' with the specific algorithm 'LightGBM algorithm'. It uses a specific verb ('predict') and identifies the resource ('incident') and what gets predicted. However, it doesn't explicitly differentiate from sibling tools like 'ml_predict_change_risk' or 'ml_train_incident_classifier', though the focus on incident categorization is clear.

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 guidance on when to use this tool versus alternatives. It mentions 'latest release: LightGBM algorithm' which hints at model versioning, but doesn't specify use cases, prerequisites, or exclusions. Given the many sibling tools including other ML tools, this lack of comparative guidance is a significant gap.

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